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

    Neuronpedia

    INDEX
    Explanations

    frequency varies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posticis
    0.50
     tsunami
    0.49
    ٹو
    0.48
     salivary
    0.48
     ۳
    0.47
     repre
    0.47
     localVarAccept
    0.47
     antibiotic
    0.46
    ⦖
    0.46
     bipartisan
    0.46
    POSITIVE LOGITS
    貨
    0.47
    狗
    0.45
    talent
    0.44
    裁
    0.43
    api
    0.43
    dao
    0.43
    wens
    0.42
    關
    0.42
    外部
    0.41
    棄
    0.41
    Act Density 0.001%

    No Known Activations