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

    Neuronpedia

    INDEX
    Explanations

    please read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    であ
    0.79
    dehyde
    0.72
    こと
    0.71
     galima
    0.70
     a
    0.70
    か
    0.68
    요
    0.66
     depende
    0.66
    ೊಂಡು
    0.66
    nál
    0.66
    POSITIVE LOGITS
    كم
    0.80
    hiv
    0.77
     Pals
    0.77
    ್‌
    0.75
    هم
    0.75
    न्स
    0.73
    اعة
    0.73
    ٰ
    0.73
    hah
    0.73
    ُ
    0.73
    Act Density 0.005%

    No Known Activations