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

    Neuronpedia

    INDEX
    Explanations

    severity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pill
    -0.07
    وست
    -0.07
    lossen
    -0.07
    .salary
    -0.06
    "title
    -0.06
     sezon
    -0.06
    (sprite
    -0.06
     Fib
    -0.06
     purification
    -0.06
    ffset
    -0.06
    POSITIVE LOGITS
    بير
    0.07
    ری
    0.06
    ────
    0.06
    iclass
    0.06
    esseract
    0.06
    -components
    0.06
    @author
    0.06
     řád
    0.06
    .oauth
    0.06
    =int
    0.06
    Act Density 0.011%

    No Known Activations