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

    Neuronpedia

    INDEX
    Explanations

    hills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    3.82
    ה
    3.66
    ים
    3.63
    ς
    3.37
    ের
    3.08
    schnitt
    2.97
    ા
    2.91
    a
    2.86
    s
    2.79
    多い
    2.73
    POSITIVE LOGITS
    कृष्ण
    3.25
    ного
    3.12
    กก
    2.99
    ので
    2.77
    ic
    2.74
    क
    2.71
    2.70
    billy
    2.70
    يه
    2.66
     ಇತರ
    2.63
    Act Density 0.060%

    No Known Activations