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

    Neuronpedia

    INDEX
    Explanations

    barre chords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nent
    1.05
    Рус
    1.03
    。\
    1.02
    "+"|".
    1.02
    انے
    0.99
     OPD
    0.99
    ِّف
    0.98
    мін
    0.96
    ;</
    0.96
    Յ
    0.96
    POSITIVE LOGITS
    ו
    1.39
     was
    1.33
    on
    1.28
    ó
    1.28
    و
    1.27
    at
    1.27
     it
    1.27
    리
    1.27
     will
    1.22
     the
    1.20
    Act Density 0.000%

    No Known Activations