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

    Neuronpedia

    INDEX
    Explanations

    masked identifiers and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ter
    0.74
    de
    0.71
    z
    0.69
    are
    0.68
    and
    0.65
    ale
    0.64
    ~\
    0.64
     agron
    0.63
    ert
    0.62
    chun
    0.61
    POSITIVE LOGITS
    urètre
    0.66
    дет
    0.64
    料金
    0.64
    قیم
    0.64
    נו
    0.60
    概要
    0.60
    铀
    0.60
    وی
    0.59
    ционными
    0.59
    ры
    0.59
    Act Density 0.021%

    No Known Activations