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

    Neuronpedia

    INDEX
    Explanations

    scheduling and optimizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಹಾರ
    0.45
    数値
    0.44
    実装
    0.44
     seizures
    0.42
     व्यवहार
    0.42
    中止
    0.42
     карте
    0.42
    逑
    0.42
    衄
    0.41
    簡単な
    0.41
    POSITIVE LOGITS
     develops
    0.45
     London
    0.44
     replaces
    0.42
     closely
    0.41
     arranges
    0.40
    돌
    0.40
    doll
    0.40
     addresses
    0.39
     comprised
    0.39
    London
    0.38
    Act Density 0.004%

    No Known Activations