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

    Neuronpedia

    INDEX
    Explanations

    starting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Datuak
    -0.66
    出版年
    -0.65
     nahilalakip
    -0.62
    fastjson
    -0.61
    PRNewswire
    -0.60
     ſever
    -0.57
    databind
    -0.57
    DIPSETTING
    -0.56
     autorytatywna
    -0.55
    INCREF
    -0.54
    POSITIVE LOGITS
     étant
    0.49
    let
    0.49
     Leave
    0.49
    Follow
    0.48
     informée
    0.48
    ionato
    0.47
     Follow
    0.47
    leave
    0.47
     Keep
    0.46
    Leave
    0.46
    Act Density 0.001%

    No Known Activations