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

    Neuronpedia

    INDEX
    Explanations

    extracting information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     runny
    0.70
    ovane
    0.69
    en
    0.68
    徑
    0.66
    替
    0.66
    دي
    0.65
    ^{-}\
    0.62
     khắc
    0.62
    േന
    0.62
    ConformanceMode
    0.62
    POSITIVE LOGITS
    Quel
    0.69
    androidx
    0.67
    ступ
    0.67
    ists
    0.66
    苦
    0.66
    斗
    0.66
    ো
    0.66
     gleaned
    0.65
     neo
    0.64
    ശ്വാ
    0.64
    Act Density 0.090%

    No Known Activations