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

    Neuronpedia

    INDEX
    Explanations

    Core Principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Festival
    0.37
    ivos
    0.37
     Pier
    0.35
     يلي
    0.35
     الخلف
    0.34
    嵌套
    0.34
    setLayout
    0.34
    spring
    0.34
    üns
    0.33
     اسئله
    0.33
    POSITIVE LOGITS
    ᱛ
    0.43
     हथ
    0.43
     ketone
    0.41
    리기
    0.41
    Dopo
    0.40
     cocon
    0.39
     dokumen
    0.38
    wirkung
    0.38
    XA
    0.38
     booze
    0.38
    Act Density 0.000%

    No Known Activations