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

    Neuronpedia

    INDEX
    Explanations

    classification systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reaching
    -0.07
     Hom
    -0.07
    텃
    -0.07
     Invent
    -0.07
    졌다
    -0.06
    LEAR
    -0.06
    IVERS
    -0.06
    �
    -0.06
     Zu
    -0.06
     Đi
    -0.06
    POSITIVE LOGITS
    十余年
    0.07
    黟
    0.07
    -chat
    0.07
    rupted
    0.07
     Kafka
    0.07
    公安局
    0.07
    uards
    0.07
    omaly
    0.07
    multi
    0.07
    Serial
    0.07
    Act Density 0.032%

    No Known Activations