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

    Neuronpedia

    INDEX
    Explanations

    Azerbaijan and Azerbaijani

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ō
    0.88
    د
    0.80
    س
    0.78
     Ā
    0.77
     Suzhou
    0.73
    دق
    0.72
     concreta
    0.71
    ד
    0.70
     out
    0.70
     aparece
    0.70
    POSITIVE LOGITS
    m
    0.84
    ol
    0.83
    r
    0.80
    ty
    0.70
    on
    0.67
    lar
    0.67
    en
    0.66
    b
    0.65
    il
    0.64
    sof
    0.64
    Act Density 0.001%

    No Known Activations