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

    Neuronpedia

    INDEX
    Explanations

    -based

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _deposit
    -0.07
    辈子
    -0.06
    救助
    -0.06
    人民
    -0.06
     vinyl
    -0.06
     Nurse
    -0.06
    红酒
    -0.06
     meshes
    -0.06
     Superv
    -0.06
    炉
    -0.06
    POSITIVE LOGITS
    الأردن
    0.07
    >alert
    0.07
    ostringstream
    0.07
     أفري
    0.07
    (red
    0.06
    '"
    0.06
    𝔷
    0.06
    .strip
    0.06
    (author
    0.06
    .GetById
    0.06
    Act Density 0.002%

    No Known Activations