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

    Neuronpedia

    INDEX
    Explanations

    as if scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vibrations
    0.43
    ទំនាក់
    0.40
     blurry
    0.39
    s
    0.39
     M
    0.39
     ไ
    0.39
     मिलेंगे
    0.39
     แ
    0.38
     sätt
    0.38
     mitigation
    0.38
    POSITIVE LOGITS
    ને
    0.42
    ovis
    0.42
    ivesse
    0.42
     იყოს
    0.41
    라도
    0.40
    ਨ
    0.40
     být
    0.39
    opez
    0.39
    itoare
    0.39
    এটি
    0.38
    Act Density 0.026%

    No Known Activations