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

    Neuronpedia

    INDEX
    Explanations

    limited or less

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.86
    v
    0.65
    r
    0.63
    ab
    0.61
    ad
    0.58
    il
    0.58
    is
    0.57
    st
    0.57
    a
    0.55
    '
    0.55
    POSITIVE LOGITS
    ເຈ
    0.49
    фта
    0.49
    CHARS
    0.46
    აწილ
    0.46
     لوبې
    0.46
    각형
    0.45
    TARGETTING
    0.45
    cpuCycle
    0.45
    తర
    0.44
    열
    0.44
    Act Density 0.006%

    No Known Activations