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

    Neuronpedia

    INDEX
    Explanations

    parenthesized phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     samoglas
    0.41
     proguardFiles
    0.41
     I
    0.39
     selectInput
    0.38
     （
    0.38
     vutta
    0.38
     leafy
    0.37
    гүй
    0.37
    บา
    0.37
    बाजी
    0.36
    POSITIVE LOGITS
    ing
    0.77
     of
    0.71
    ة
    0.69
    u
    0.66
     are
    0.65
    a
    0.64
    ),
    0.64
    )
    0.64
    of
    0.62
    ı
    0.60
    Act Density 1.033%

    No Known Activations