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

    Neuronpedia

    INDEX
    Explanations

    insistence on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     издание
    0.93
    ArchiveAction
    0.84
    ాన్
    0.84
    л
    0.81
    ெடுக்க
    0.77
     обеспечить
    0.76
    kość
    0.76
     Многие
    0.76
    سازی
    0.75
     trzy
    0.74
    POSITIVE LOGITS
    le
    0.80
    r
    0.71
    it
    0.71
    َہ
    0.70
    t
    0.69
     vowels
    0.68
     punctuation
    0.65
    asked
    0.64
    랭
    0.64
     말투
    0.64
    Act Density 0.629%

    No Known Activations