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

    Neuronpedia

    INDEX
    Explanations

    theoretical minimum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     क्वेश्च
    0.61
    ྥ
    0.60
     マルチ
    0.59
    <unused253>
    0.57
    <unused184>
    0.57
     TNumber
    0.56
     ایپل
    0.56
     hMut
    0.55
    <unused2109>
    0.55
     सूत्रकृ
    0.55
    POSITIVE LOGITS
    .
    0.59
    M
    0.58
    age
    0.56
    ra
    0.54
    ap
    0.53
    '
    0.53
    plate
    0.52
    ag
    0.51
    ren
    0.51
    0.51
    Act Density 0.001%

    No Known Activations