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

    Neuronpedia

    INDEX
    Explanations

    lists and structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     国家
    0.44
     dham
    0.40
    ద్దా
    0.37
     पारा
    0.36
    বায়দুল
    0.36
    विच
    0.36
     weib
    0.36
     alturas
    0.36
     nal
    0.35
     Spanien
    0.35
    POSITIVE LOGITS
    profiss
    0.42
    formen
    0.38
     isolation
    0.37
    orme
    0.37
    键
    0.37
     overflow
    0.37
    HEP
    0.37
    輸
    0.36
    പ്ര
    0.36
    cellular
    0.36
    Act Density 0.001%

    No Known Activations