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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aska
    -0.07
    廓
    -0.07
    解释
    -0.07
     uçak
    -0.07
     Soviet
    -0.07
     stare
    -0.07
    缶
    -0.07
    ([^
    -0.07
    extension
    -0.07
    /Add
    -0.07
    POSITIVE LOGITS
     בגלל
    0.08
    								↵
    0.07
    ynomials
    0.07
    -feedback
    0.07
    蒗
    0.07
     ברח
    0.07
    🇿
    0.07
    ripper
    0.07
    >true
    0.07
    רכש
    0.07
    Act Density 0.019%

    No Known Activations