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

    Neuronpedia

    INDEX
    Explanations

    ое снаб, водо

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിച്ചി
    0.38
    roxine
    0.38
     সিন
    0.36
     argued
    0.36
     authentic
    0.35
     الفق
    0.35
    setWidth
    0.35
    }_{[
    0.35
    က
    0.35
     pall
    0.35
    POSITIVE LOGITS
    снаб
    0.63
    ostro
    0.57
     водо
    0.57
    от
    0.53
    opod
    0.52
    onos
    0.50
     наро
    0.48
    люби
    0.48
    od
    0.47
    провод
    0.47
    Act Density 0.003%

    No Known Activations