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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mate
    -0.07
    (builder
    -0.07
     par
    -0.06
     时
    -0.06
     override
    -0.06
    _plus
    -0.06
     ฿
    -0.06
    comments
    -0.06
     sterling
    -0.06
    \Facades
    -0.06
    POSITIVE LOGITS
    .Manager
    0.07
    _expiry
    0.07
    大阪
    0.06
    _FM
    0.06
    nginx
    0.06
    등학교
    0.06
    ád
    0.06
     sucht
    0.06
     harek
    0.06
    “That
    0.06
    Act Density 0.006%

    No Known Activations