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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Graphic
    -0.07
     drama
    -0.07
    眬
    -0.07
    .pushButton
    -0.07
    惘
    -0.07
    Ӕ
    -0.06
    עצב
    -0.06
    аз
    -0.06
    耵
    -0.06
    颋
    -0.06
    POSITIVE LOGITS
     targeting
    0.07
    真实
    0.07
    可疑
    0.07
    ائ
    0.07
    ccount
    0.07
    itably
    0.06
    金融服务
    0.06
     предложения
    0.06
    [n
    0.06
    amodel
    0.06
    Act Density 0.003%

    No Known Activations