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

    Neuronpedia

    INDEX
    Explanations

    mentions of danger to life or life saving measures

    oai_token-act-pair · gemini-2.0-flash

    life-or-death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lifetime
    -0.67
     lifetime
    -0.61
    lifetime
    -0.60
     Lifetime
    -0.59
     lifelong
    -0.57
     sociaux
    -0.51
    õi
    -0.49
    opus
    -0.48
     lifestyle
    -0.47
    AutoScaleMode
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.91
     Efq
    0.88
     Monfieur
    0.85
     Majefty
    0.77
     houſe
    0.75
     Conſ
    0.75
    SequentialGroup
    0.74
     purpoſe
    0.73
     Jefus
    0.71
    WriteLiteral
    0.71
    Act Density 0.681%

    No Known Activations