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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ذات
    -0.08
     disguise
    -0.07
    alah
    -0.07
    customers
    -0.06
    報告
    -0.06
     discouraged
    -0.06
    ierrez
    -0.06
     hurried
    -0.06
    قات
    -0.06
    -find
    -0.06
    POSITIVE LOGITS
     الکتر
    0.06
    =*/
    0.06
     tidy
    0.06
    (using
    0.06
     bicycle
    0.06
     Tube
    0.06
    /setup
    0.06
     Earth
    0.06
     Тут
    0.06
    扶
    0.06
    Act Density 0.000%

    No Known Activations