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

    Neuronpedia

    INDEX
    Explanations

    steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Huss
    -0.07
    -medium
    -0.06
    TAIL
    -0.06
    Deaths
    -0.06
    (device
    -0.06
    rows
    -0.06
    isoft
    -0.06
    ені
    -0.06
    $
    -0.06
     Kur
    -0.06
    POSITIVE LOGITS
    bcrypt
    0.07
     مواطنة
    0.06
    ственно
    0.06
    िनट
    0.06
     Michelle
    0.06
     configure
    0.06
    ;\">
    0.06
    ClearColor
    0.06
     سبتمبر
    0.06
    crud
    0.06
    Act Density 0.051%

    No Known Activations