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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ro
    -0.07
    ften
    -0.07
     orch
    -0.06
    การ
    -0.06
    =============↵
    -0.06
    реть
    -0.06
    ोख
    -0.06
     Joi
    -0.06
     арми
    -0.06
     TypeInfo
    -0.06
    POSITIVE LOGITS
    网刊下载次数
    0.06
    baugh
    0.06
    ้าของ
    0.06
    _calendar
    0.06
     hoe
    0.06
     네
    0.06
    ories
    0.06
     buz
    0.06
     hover
    0.06
    .temp
    0.06
    Act Density 0.018%

    No Known Activations