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

    Neuronpedia

    INDEX
    Explanations

    Repository

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONTROLLER
    -0.07
    Notice
    -0.06
    -fontawesome
    -0.06
     Hurt
    -0.06
     انقلاب
    -0.06
    不能
    -0.06
     podařilo
    -0.06
     желуд
    -0.06
    ladım
    -0.06
    antium
    -0.05
    POSITIVE LOGITS
     Shane
    0.07
     الملك
    0.06
     Caller
    0.06
    ／:
    0.06
    getDoctrine
    0.06
    NavigationBar
    0.06
     asia
    0.06
    Daniel
    0.06
    ty
    0.06
    ôme
    0.06
    Act Density 0.001%

    No Known Activations