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

    Neuronpedia

    INDEX
    Explanations

    features and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jeopardy
    0.64
    భవ
    0.63
     ikut
    0.61
     громад
    0.59
     ছন্দ
    0.59
     गेंद
    0.58
     kans
    0.58
    ्मण
    0.56
     Abend
    0.56
     prawd
    0.56
    POSITIVE LOGITS
     features
    5.59
     Features
    5.41
    Features
    5.20
    features
    5.12
     feature
    4.93
     Feature
    4.59
    Feature
    4.56
    feature
    4.54
     FEATURES
    4.52
     fitur
    4.10
    Act Density 0.991%

    No Known Activations