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

    Neuronpedia

    INDEX
    Explanations

    recognize or identify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restraining
    1.42
    रोवर
    1.37
    у
    1.34
    ناک
    1.33
    ам
    1.32
    atual
    1.31
    dato
    1.31
    وَ
    1.30
     scattering
    1.29
     useAppContext
    1.29
    POSITIVE LOGITS
    м
    1.32
    ا
    1.31
    ,\,
    1.31
    そろ
    1.25
    a
    1.25
     indisc
    1.24
    ства
    1.21
     dawned
    1.21
    eek
    1.17
    পর্ব
    1.17
    Act Density 0.151%

    No Known Activations