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

    Neuronpedia

    INDEX
    Explanations

    math, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cannot
    -0.06
    removed
    -0.06
     몇
    -0.06
     spat
    -0.06
     chocol
    -0.06
     appraisal
    -0.06
    ']))
↵
    -0.06
    -example
    -0.06
    _pos
    -0.06
     ")↵
    -0.06
    POSITIVE LOGITS
    ograf
    0.07
    ály
    0.07
    ackBar
    0.06
    /////////////////////////////////////////////////////////////////////////////↵
    0.06
    contents
    0.06
     Valor
    0.06
    城市
    0.06
    fl
    0.06
     calidad
    0.06
    agem
    0.06
    Act Density 0.022%

    No Known Activations