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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.60
    is
    0.59
    da
    0.58
    nt
    0.57
    For
    0.56
    nd
    0.55
    ats
    0.55
    us
    0.54
    ists
    0.54
    ics
    0.53
    POSITIVE LOGITS
     европей
    0.51
    ləş
    0.50
     الطلبه
    0.49
    PAssignment
    0.48
    رسٹ
    0.48
     خمسه
    0.47
     جمله
    0.47
     IntegerValue
    0.47
     uye
    0.47
     baseApiPath
    0.47
    Act Density 0.000%

    No Known Activations