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

    Neuronpedia

    INDEX
    Explanations

    appropriate responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -store
    -0.07
    psilon
    -0.07
    serial
    -0.07
    bei
    -0.07
    cover
    -0.07
    rels
    -0.06
    dent
    -0.06
    plants
    -0.06
    poses
    -0.06
    ersion
    -0.06
    POSITIVE LOGITS
     uyar
    0.06
    ิญญ
    0.06
     Nicht
    0.06
     trochu
    0.06
     och
    0.06
     진짜
    0.06
    发送
    0.06
    _PC
    0.06
    няя
    0.06
    !")↵↵
    0.06
    Act Density 0.003%

    No Known Activations