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

    Neuronpedia

    INDEX
    Explanations

    regex matching and extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protrusions
    0.49
     чисто
    0.49
     discretized
    0.48
     fractional
    0.46
     anod
    0.45
     diode
    0.44
    nění
    0.44
    \
    0.44
    inse
    0.44
    times
    0.44
    POSITIVE LOGITS
    αι
    0.54
    學校
    0.53
    稱
    0.52
     INDIA
    0.47
     FALL
    0.47
     EVEN
    0.47
    ב
    0.47
    棋
    0.46
    ερ
    0.46
    𝗽
    0.46
    Act Density 0.001%

    No Known Activations