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

    Neuronpedia

    INDEX
    Explanations

    concluding statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.68
    0
    0.58
    0.52
    zter
    0.52
    IS
    0.51
    i
    0.48
    大
    0.48
    lite
    0.47
    define
    0.47
    see
    0.46
    POSITIVE LOGITS
    고
    0.75
     can
    0.66
    ле
    0.60
    к
    0.56
    ли
    0.54
    ía
    0.52
    но
    0.51
    ться
    0.51
     пол
    0.50
    ئة
    0.50
    Act Density 0.769%

    No Known Activations