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

    Neuronpedia

    INDEX
    Explanations

    tables and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rist
    0.49
    ötzlich
    0.47
    ıma
    0.46
    تاة
    0.45
    anggil
    0.45
    ریف
    0.43
     powodu
    0.42
    ahankan
    0.42
    ූ
    0.42
    iellement
    0.41
    POSITIVE LOGITS
     table
    0.98
     Table
    0.89
    Table
    0.89
     جدول
    0.76
    table
    0.75
     Tabelle
    0.75
    各
    0.75
     comparison
    0.74
    TABLE
    0.73
     tabular
    0.72
    Act Density 0.336%

    No Known Activations