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

    Neuronpedia

    INDEX
    Explanations

    legality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ................................................................
    -0.07
     yüks
    -0.07
    	that
    -0.07
    栌
    -0.07
    Ẋ
    -0.07
    💊
    -0.07
    缴
    -0.07
     Cash
    -0.07
    	pc
    -0.07
    供应商
    -0.07
    POSITIVE LOGITS
    �
    0.07
    त
    0.07
    ２
    0.06
     MAL
    0.06
     sighting
    0.06
    _OVER
    0.06
    _SORT
    0.06
    Ideal
    0.06
     iterating
    0.06
    .Photo
    0.06
    Act Density 0.080%

    No Known Activations