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

    Neuronpedia

    INDEX
    Explanations

    hyphens and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     שנים
    -0.08
     sign
    -0.07
    关节
    -0.07
     Españ
    -0.07
     rotational
    -0.07
     Revenue
    -0.06
    .getAs
    -0.06
     Obj
    -0.06
    饲养
    -0.06
     מערכת
    -0.06
    POSITIVE LOGITS
     default
    0.07
    之下
    0.07
    尝
    0.07
    🖱
    0.07
    نغ
    0.07
     dick
    0.07
    Urls
    0.07
    _MODAL
    0.07
     model
    0.07
     NSAttributedString
    0.06
    Act Density 0.204%

    No Known Activations