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

    Neuronpedia

    INDEX
    Explanations

    generating lists and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rizio
    0.90
    无数
    0.83
     niekoľ
    0.82
    larla
    0.81
    ებს
    0.81
     birkaç
    0.81
    retched
    0.79
    三大
    0.78
     awhile
    0.76
    ęs
    0.75
    POSITIVE LOGITS
    +
    1.77
    0
    1.55
     distinct
    1.53
    %
    1.50
     మంది
    1.47
    개의
    1.44
    টি
    1.40
     જેટ
    1.39
     adet
    1.35
     개의
    1.25
    Act Density 0.243%

    No Known Activations