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

    Neuronpedia

    INDEX
    Explanations

    through [positive outcome]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.77
    ات
    1.67
    soldiers
    1.33
    The
    1.22
    GES
    1.11
    de
    1.10
    parties
    1.09
    symbols
    1.09
    Volume
    1.08
    1.07
    POSITIVE LOGITS
    齬
    1.41
    ம்
    1.36
     pediu
    1.36
    ic
    1.34
     tendrá
    1.31
     moistur
    1.30
    的に
    1.28
     miał
    1.28
    랐
    1.27
    ו
    1.27
    Act Density 0.016%

    No Known Activations