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

    Neuronpedia

    INDEX
    Explanations

    timeout, hour, started, time, range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nailed
    1.31
     wrongfully
    1.26
    ylated
    1.25
    苣
    1.23
    萆
    1.23
    ynu
    1.23
     क्वाड्रेटिक
    1.23
    𝓌
    1.21
    ไน
    1.21
     breezes
    1.20
    POSITIVE LOGITS
    s
    1.39
    on
    1.38
    et
    1.12
     گے
    1.10
    l
    1.07
    m
    1.07
    lapping
    1.03
    iant
    1.02
    r
    1.01
     Dissertation
    1.01
    Act Density 0.000%

    No Known Activations