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

    Neuronpedia

    INDEX
    Explanations

    judging criteria

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	headers
    -0.07
     adhere
    -0.07
     spelled
    -0.07
     öz
    -0.07
     Differences
    -0.07
     cole
    -0.07
    /locale
    -0.06
     Eğitim
    -0.06
    脈
    -0.06
     uyarı
    -0.06
    POSITIVE LOGITS
    万台
    0.07
    .frequency
    0.07
    机器人
    0.06
    บท
    0.06
    Robin
    0.06
     Challenges
    0.06
    ()`
    0.06
    ObjectOfType
    0.06
    BTC
    0.06
    톤
    0.06
    Act Density 0.065%

    No Known Activations