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

    Neuronpedia

    INDEX
    Explanations

    sturdy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ясь
    1.25
    و
    1.17
    િંગ
    1.11
    ální
    1.09
    astă
    1.08
    utico
    1.08
    uí
    1.07
    acariy
    1.05
    ো
    1.04
    ac
    1.03
    POSITIVE LOGITS
    0
    2.08
    1
    1.61
     to
    1.50
    na
    1.36
    9
    1.30
    8
    1.27
    </h2>
    1.25
     are
    1.21
    م
    1.20
     you
    1.17
    Act Density 0.000%

    No Known Activations