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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dang
    -0.07
     doping
    -0.07
    年薪
    -0.07
     camel
    -0.07
     appeals
    -0.06
    ,:]
    -0.06
    =@
    -0.06
     varying
    -0.06
     marry
    -0.06
    ]*)
    -0.06
    POSITIVE LOGITS
    夸
    0.07
     rápido
    0.07
    pressions
    0.07
     DIRECTORY
    0.07
    市场上
    0.07
    Թ
    0.07
     لتحقيق
    0.07
     Kafka
    0.07
     Büro
    0.06
     PHONE
    0.06
    Act Density 0.005%

    No Known Activations