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

    Neuronpedia

    INDEX
    Explanations

    important note

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    0.99
    ت
    0.90
    у
    0.80
    ggi
    0.77
    구
    0.77
    ొ
    0.75
    lı
    0.75
    জানা
    0.73
    кат
    0.72
     golongan
    0.72
    POSITIVE LOGITS
    ಛ
    0.89
     هذه
    0.88
     cautions
    0.88
    方位
    0.87
     organismos
    0.86
     pública
    0.82
     these
    0.82
     υπάρχει
    0.81
     palmit
    0.81
    没有
    0.80
    Act Density 0.450%

    No Known Activations