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

    Neuronpedia

    INDEX
    Explanations

    a variety of different programming syntax and possibly HTML

    oai_token-act-pair · gemini-2.0-flash

    sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.71
    bcryptjs
    -0.58
    .

    -0.58
     (

    -0.56
     = 
    -0.56
    +

    -0.55
     $=
    -0.54
    )

    -0.54
    )​
    -0.54
     gian
    -0.53
    POSITIVE LOGITS
    <bos>
    2.14
     itſelf
    0.65
     himſelf
    0.57
    sizeCache
    0.56
     professionali
    0.52
     Monfieur
    0.52
    The
    0.51
     reaſon
    0.50
     whoſe
    0.50
     purpoſe
    0.49
    Act Density 0.453%
    No Known Activations