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

    Neuronpedia

    INDEX
    Explanations

    * symbols and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ött
    0.44
    も
    0.44
     шла
    0.44
     ബാല
    0.44
    ಔ
    0.44
    ਣੀ
    0.43
    \})
    0.43
    AttributedString
    0.42
     драмати
    0.42
    horizontalLayout
    0.42
    POSITIVE LOGITS
     app
    0.45
     Commencement
    0.44
    样子
    0.43
    party
    0.42
     extra
    0.41
     App
    0.41
     Bueno
    0.41
     geo
    0.41
     party
    0.40
    called
    0.39
    Act Density 0.021%

    No Known Activations