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

    Neuronpedia

    INDEX
    Explanations

    prefix characters like %, \, ►

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    0.93
     and
    0.93
    E
    0.89
    A
    0.88
     was
    0.86
    ,
    0.83
    O
    0.82
    Ì
    0.82
    I
    0.81
    U
    0.81
    POSITIVE LOGITS
    s
    1.02
    ти
    0.81
     مرتبط
    0.80
    "。
    0.77
     sasane
    0.77
    liğini
    0.76
    לות
    0.75
     非
    0.75
    dengan
    0.75
    ский
    0.74
    Act Density 0.114%

    No Known Activations