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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries about identity and self-reflection

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

    Questions asked or statements made to "you," "we," or "it"

    np_acts-logits-general · gemini-2.0-flash

    what do you think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yes
    -0.60
    Yes
    -0.60
     Yes
    -0.56
    yes
    -0.56
    YES
    -0.51
    DebuggerNonUser
    -0.50
    definitely
    -0.49
     både
    -0.49
    TemporalType
    -0.48
     unquestionably
    -0.48
    POSITIVE LOGITS
     exactly
    1.17
    exactly
    1.00
     exactement
    0.96
     exatamente
    0.89
     Exactly
    0.88
     esattamente
    0.88
     exactamente
    0.85
     precies
    0.84
     denn
    0.79
    そんなに
    0.78
    Act Density 0.254%

    No Known Activations