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

    Neuronpedia

    INDEX
    Explanations

    files, code, or letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ンジ
    0.54
     caves
    0.52
     bushes
    0.50
     বিষয়টি
    0.49
    lığı
    0.49
     ಸಂಧಿ
    0.48
    <unused2117>
    0.47
     accuracies
    0.46
    emic
    0.46
     क्वेश्च
    0.45
    POSITIVE LOGITS
    UN
    0.56
    0.54
    ä
    0.48
    N
    0.47
    OST
    0.47
     Si
    0.46
     k
    0.46
     gol
    0.45
    and
    0.45
    L
    0.44
    Act Density 0.003%

    No Known Activations