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

    Neuronpedia

    INDEX
    Explanations

    only when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quickly
    0.62
     endless
    0.61
     rápido
    0.61
     schnell
    0.59
     rápida
    0.59
    ब
    0.59
     kurzer
    0.57
     dễ
    0.57
     zahlreichen
    0.57
     विफल
    0.57
    POSITIVE LOGITS
     본격
    1.32
    才會
    1.16
     dopiero
    1.16
    才会
    1.14
    真正
    1.10
    ようやく
    1.05
    才
    1.02
    本格
    1.01
     belated
    0.99
     pleinement
    0.96
    Act Density 0.365%

    No Known Activations