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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bid
    -0.07
     EACH
    -0.07
     Personal
    -0.07
     assistance
    -0.07
     MAY
    -0.07
    CAF
    -0.07
    航空公司
    -0.07
    .car
    -0.07
    _construct
    -0.06
    合作伙伴
    -0.06
    POSITIVE LOGITS
    焚烧
    0.08
    🌩
    0.07
    ("/")↵
    0.07
    惯例
    0.07
    -fired
    0.07
    �
    0.07
    後の
    0.07
    ック
    0.07
     самого
    0.06
    껌
    0.06
    Act Density 0.351%

    No Known Activations