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

    Neuronpedia

    INDEX
    Explanations

    include guards and preprocessor directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.71
     of
    0.71
    ='
    0.69
    s
    0.68
     with
    0.64
     digit
    0.60
     simple
    0.59
     pomo
    0.58
     bantu
    0.58
     shuffling
    0.57
    POSITIVE LOGITS
    اه
    0.81
    ா
    0.65
    itación
    0.64
    า
    0.64
    ные
    0.64
    اض
    0.64
    此同时
    0.63
    Watercolor
    0.63
    Usually
    0.63
    ା
    0.63
    Act Density 0.001%

    No Known Activations