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

    Neuronpedia

    INDEX
    Explanations

    pandas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evolved
    -0.07
    的笑容
    -0.07
     Każdy
    -0.07
     modulus
    -0.06
     лю
    -0.06
     Julien
    -0.06
    ListItem
    -0.06
     sharing
    -0.06
    Visit
    -0.06
    player
    -0.06
    POSITIVE LOGITS
    𬒈
    0.08
    挂牌
    0.08
    _PROGRAM
    0.07
     Blueprint
    0.07
    团圆
    0.07
    czeń
    0.07
    ثان
    0.06
    _managed
    0.06
    _trade
    0.06
    anguage
    0.06
    Act Density 0.003%

    No Known Activations