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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Series
    -0.07
    왔
    -0.07
     Sachs
    -0.06
     ACA
    -0.06
    _parents
    -0.06
    アップ
    -0.06
    optera
    -0.06
    Unlock
    -0.06
    /head
    -0.06
     includes
    -0.06
    POSITIVE LOGITS
    percentage
    0.07
    ços
    0.07
    (texture
    0.07
    :")↵
    0.06
    	product
    0.06
    ボ
    0.06
     disclosure
    0.06
     bisc
    0.06
     ostensibly
    0.06
    وية
    0.06
    Act Density 0.019%

    No Known Activations