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

    Neuronpedia

    INDEX
    Explanations

    technical followed by specifications or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ті
    1.15
    ное
    1.13
    ﺖ
    1.11
    ta
    1.09
    மாக
    1.07
    om
    1.06
    tahun
    1.04
    та
    1.03
    tempo
    1.03
     toothpick
    1.03
    POSITIVE LOGITS
    b
    1.31
    c
    1.25
    е
    1.20
    其他
    1.14
    <
    1.11
    ה
    1.11
    x
    1.10
    ב
    1.10
    d
    1.07
    小
    1.05
    Act Density 0.079%

    No Known Activations