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

    Neuronpedia

    INDEX
    Explanations

    www

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (attributes
    -0.07
     Alfred
    -0.07
    VRT
    -0.07
     reinforces
    -0.07
     expertise
    -0.07
    冰箱
    -0.07
    Trim
    -0.07
    итет
    -0.07
    问世
    -0.07
    ])+
    -0.07
    POSITIVE LOGITS
    Ę
    0.07
     Während
    0.07
    しま
    0.07
    ера
    0.07
    ከ
    0.07
    án
    0.07
    良く
    0.06
     voted
    0.06
    职工
    0.06
    瘼
    0.06
    Act Density 0.004%

    No Known Activations