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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ann
    -0.52
    out
    -0.52
    teen
    -0.51
    set
    -0.50
    dep
    -0.50
    at
    -0.49
    side
    -0.49
    hill
    -0.49
     before
    -0.48
    kı
    -0.48
    POSITIVE LOGITS
     NUKAT
    0.92
     autorytatywna
    0.91
    thâu
    0.90
     resourceCulture
    0.81
     ProtoMessage
    0.81
    EDEFAULT
    0.80
     виправивши
    0.75
     ligiloj
    0.71
    ollectionView
    0.69
     légales
    0.69
    Act Density 0.153%

    No Known Activations