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

    Neuronpedia

    INDEX
    Explanations

    comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ي
    -0.07
    egration
    -0.06
    (___
    -0.06
     Carpet
    -0.06
    ipped
    -0.06
    STEP
    -0.06
    ارة
    -0.06
    -shop
    -0.06
    躬
    -0.06
     light
    -0.06
    POSITIVE LOGITS
     ACC
    0.07
     Produkt
    0.07
    emory
    0.07
    达到了
    0.07
    Blo
    0.07
    .effect
    0.06
     dic
    0.06
    (success
    0.06
     umo
    0.06
     haciendo
    0.06
    Act Density 0.234%

    No Known Activations