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

    Neuronpedia

    INDEX
    Explanations

    eye

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     된다
    -0.07
     viet
    -0.07
     Crud
    -0.07
     inconsistencies
    -0.07
     capabilities
    -0.07
    .undo
    -0.07
    裁
    -0.07
    帮助
    -0.06
     Интернет
    -0.06
    ations
    -0.06
    POSITIVE LOGITS
    ("{}
    0.07
    _ENTITY
    0.07
    中国企业
    0.07
    ZE
    0.07
    龙泉
    0.06
    .partial
    0.06
    哲学
    0.06
    应收账
    0.06
    _Return
    0.06
    װ
    0.06
    Act Density 0.008%

    No Known Activations