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

    Neuronpedia

    INDEX
    Explanations

    worth it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    1.13
    is
    1.00
    ot
    0.98
    en
    0.96
    an
    0.95
    od
    0.93
    el
    0.90
    isers
    0.89
    ing
    0.89
    ien
    0.89
    POSITIVE LOGITS
    s
    1.00
     prosent
    0.82
    ين
    0.80
    ১৪
    0.78
    ’
    0.77
    يا
    0.76
    پ
    0.75
    (
    0.74
    泗
    0.74
    AL
    0.73
    Act Density 0.008%

    No Known Activations