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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating user consent and acceptance related to website usage and cookies

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

    agree to terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.54
    AccessorTable
    -0.54
    __':
    -0.53
    Попис
    -0.52
     esternos
    -0.52
     CallOverrides
    -0.50
    GraphicsUnit
    -0.50
    richTextPanel
    -0.50
     برانيه
    -0.49
     Uncertain
    -0.49
    POSITIVE LOGITS
     consciência
    0.37
     tacón
    0.36
     asupra
    0.35
    äsche
    0.33
     Widerspruch
    0.33
    ofern
    0.32
     gedrag
    0.32
    accept
    0.32
     accepted
    0.32
     acceptance
    0.31
    Act Density 0.043%

    No Known Activations