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

    Neuronpedia

    INDEX
    Explanations

    algorithm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    إصدار
    -0.07
    >>,
    -0.07
     imageName
    -0.07
    'est
    -0.07
    ('[
    -0.07
    $temp
    -0.06
    "http
    -0.06
     rewarding
    -0.06
     '!
    -0.06
     japanese
    -0.06
    POSITIVE LOGITS
    (tokens
    0.08
     leuk
    0.07
     Pand
    0.07
    有可能
    0.07
     sö
    0.07
    ,))↵
    0.07
     evidenced
    0.07
     bases
    0.06
     polit
    0.06
     bath
    0.06
    Act Density 0.001%

    No Known Activations