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

    Neuronpedia

    INDEX
    Explanations

    skin, food, and sleep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.76
    z
    0.76
    其他
    0.59
    أ
    0.59
    ar
    0.59
    v
    0.57
    A
    0.55
    ز
    0.55
    in
    0.53
    ဆေး
    0.52
    POSITIVE LOGITS
    ’
    0.68
    ambilan
    0.60
     Những
    0.59
    kenalkan
    0.59
     Familie
    0.58
    つ
    0.56
     युवाओ
    0.54
     Knoten
    0.54
     kilometre
    0.54
     Lobkovic
    0.54
    Act Density 0.065%

    No Known Activations