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

    Neuronpedia

    INDEX
    Explanations

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.38
    t
    1.28
    Y
    1.13
     niya
    1.12
     불구하고
    1.12
             
    1.10
    tops
    1.09
    u
    1.07
    highway
    1.06
    er
    1.01
    POSITIVE LOGITS
    ামুটি
    2.06
    ை
    1.95
    い
    1.95
    ных
    1.77
    ב
    1.77
    ا
    1.67
    ો
    1.60
    не
    1.58
    ل
    1.56
    му
    1.55
    Act Density 0.112%

    No Known Activations