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

    Neuronpedia

    INDEX
    Explanations

    place name and program names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    2.04
    o
    1.98
    e
    1.95
    a
    1.93
    er
    1.68
    it
    1.56
    ه
    1.55
    ي
    1.54
    i
    1.42
    h
    1.36
    POSITIVE LOGITS
    ואה
    1.28
    был
    1.19
    駑
    1.17
     secrete
    1.17
     subchapter
    1.17
    और
    1.16
     rewire
    1.16
     nonconvex
    1.14
    neutrophiles
    1.14
     CTS
    1.12
    Act Density 0.035%

    No Known Activations