Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to avoiding spoilers in discussions about books or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Warnings about revealing private or sensitive information

    np_acts-logits-general · gemini-2.0-flash

    confidential or sensitive information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TextBoxColumn
    -0.52
    })->
    -0.51
    ExtendWith
    -0.48
     Choice
    -0.47
    makeConstraints
    -0.47
    Попис
    -0.47
    AndEndTag
    -0.46
    Choice
    -0.46
    choice
    -0.45
    Reprodução
    -0.44
    POSITIVE LOGITS
     confidential
    0.54
     tartalomajánló
    0.44
     confidentiality
    0.43
    Confidential
    0.40
    PerformLayout
    0.40
     Confidential
    0.39
    utilisons
    0.38
     ProtoMessage
    0.36
     privacy
    0.36
     незавершена
    0.36
    Act Density 0.253%

    No Known Activations