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

    Neuronpedia

    INDEX
    Explanations

    phphtmlevidenceconviction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺩ
    1.27
    са
    1.26
    ي
    1.26
    п
    1.22
    লে
    1.17
     amortization
    1.16
     matters
    1.11
    ס
    1.11
     demeanor
    1.09
     REQUI
    1.08
    POSITIVE LOGITS
    på
    1.67
     früheren
    1.55
     Orta
    1.36
     etiam
    1.34
    et
    1.34
    möglich
    1.32
    m
    1.32
    的同时
    1.31
     öğret
    1.31
    ehr
    1.31
    Act Density 0.001%

    No Known Activations