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

    Neuronpedia

    INDEX
    Explanations

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    詬
    0.42
    ="$(
    0.41
    ㇇
    0.41
    дон
    0.40
    дий
    0.39
    ักษณะ
    0.39
    奬
    0.39
    Fotos
    0.39
     Redeem
    0.38
    実験
    0.38
    POSITIVE LOGITS
     instead
    0.59
     indices
    0.53
     untouched
    0.51
     Instead
    0.47
     statt
    0.46
    instead
    0.46
     вместо
    0.43
     invece
    0.43
    Instead
    0.43
     quicker
    0.42
    Act Density 0.000%

    No Known Activations