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

    Neuronpedia

    INDEX
    Explanations

    Ending punctuation and word separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ograni
    0.59
     (
    0.59
     atract
    0.56
     intrigue
    0.56
     etiqueta
    0.56
     améli
    0.55
     exposé
    0.55
     autorisé
    0.55
     élarg
    0.54
     enthous
    0.54
    POSITIVE LOGITS
    ۔
    0.64
    .
    0.63
    _
    0.58
    נו
    0.54
    ئیں
    0.54
    는
    0.52
    ።
    0.52
    ز
    0.51
    ਆਂ
    0.50
    ที่
    0.49
    Act Density 0.111%

    No Known Activations