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

    Neuronpedia

    INDEX
    Explanations

    Internationalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اري
    -0.06
    dims
    -0.06
    /stats
    -0.06
    aire
    -0.06
     istem
    -0.06
    _Code
    -0.06
    _thresh
    -0.06
    _manual
    -0.06
    enheim
    -0.06
     rahatsız
    -0.06
    POSITIVE LOGITS
     Bloss
    0.08
    ossed
    0.07
    .k
    0.07
     immersion
    0.07
     Anchor
    0.07
    ětš
    0.06
     spanish
    0.06
    ![↵
    0.06
    (↵
    0.06
    "?↵↵
    0.06
    Act Density 0.002%

    No Known Activations