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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,arg
    -0.06
     Cosby
    -0.06
     caste
    -0.06
    aste
    -0.06
     anarchist
    -0.06
    _-_
    -0.06
     train
    -0.06
    actal
    -0.06
     aldığı
    -0.06
    煤
    -0.06
    POSITIVE LOGITS
     قص
    0.06
     сель
    0.06
     Yıl
    0.06
    γη
    0.06
     INTERN
    0.06
    ?>
↵
    0.06
    />
↵
    0.06
     unin
    0.06
    (timeout
    0.06
     chví
    0.06
    Act Density 0.015%

    No Known Activations