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

    Neuronpedia

    INDEX
    Explanations

    semiconductor patterns or shoes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.84
    ل
    0.68
    ور
    0.65
    ის
    0.64
    N
    0.62
    ர்
    0.60
    K
    0.59
    ку
    0.57
    و
    0.57
    and
    0.56
    POSITIVE LOGITS
    0.80
     to
    0.60
     is
    0.60
     С
    0.52
     Κ
    0.51
     Перейти
    0.51
    ?</
    0.51
     the
    0.51
     灬
    0.51
     dextrose
    0.50
    Act Density 7.475%

    No Known Activations