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

    Neuronpedia

    INDEX
    Explanations

    photo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ervoir
    -0.07
    绁
    -0.07
     Congressional
    -0.07
     improbable
    -0.06
    才算
    -0.06
     Mc
    -0.06
    かけて
    -0.06
     Confidence
    -0.06
     covariance
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    unidad
    0.07
    _user
    0.07
    מוני
    0.06
    Anna
    0.06
     `;↵
    0.06
    法令
    0.06
    进食
    0.06
    line
    0.06
    .RequestMethod
    0.06
    뽄
    0.06
    Act Density 0.011%

    No Known Activations