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

    Neuronpedia

    INDEX
    Explanations

    data shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    0.96
    ம்
    0.77
    い
    0.76
    ри
    0.73
    リ
    0.72
    าค
    0.71
    د
    0.69
    क
    0.67
    મ
    0.64
    ม
    0.64
    POSITIVE LOGITS
    c
    0.61
    }$&$-
    0.57
    t
    0.55
    ah
    0.54
     இருந்து
    0.54
    zeigen
    0.54
    hesda
    0.54
     vitamin
    0.53
     চেয়ারম্যান
    0.53
    ali
    0.52
    Act Density 0.000%

    No Known Activations