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

    Neuronpedia

    INDEX
    Explanations

    speed and pitch shifting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     criteri
    0.61
     imprese
    0.59
     tarixi
    0.55
     ヨコハマ
    0.52
    któ
    0.51
     関係
    0.51
     السي
    0.51
     givenChar
    0.51
    desi
    0.50
    苡
    0.50
    POSITIVE LOGITS
    import
    0.61
     et
    0.60
    رب
    0.58
     army
    0.58
     پردا
    0.57
     engines
    0.57
     Engine
    0.56
    package
    0.54
     Android
    0.54
     Dragonfly
    0.53
    Act Density 0.001%

    No Known Activations