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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shape
    -0.08
    μές
    -0.08
    ่
    -0.07
     raz
    -0.07
    된다
    -0.07
    amı
    -0.06
    ันก
    -0.06
    west
    -0.06
     використання
    -0.06
    lüğü
    -0.06
    POSITIVE LOGITS
     purchasing
    0.07
     사건
    0.06
     uphol
    0.06
     procur
    0.06
    ccess
    0.06
    firm
    0.06
     Spotlight
    0.06
    insert
    0.06
     пищ
    0.06
     reinforces
    0.06
    Act Density 0.000%

    No Known Activations