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

    Neuronpedia

    INDEX
    Explanations

    code functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kirst
    -0.07
     хол
    -0.07
     Ducks
    -0.07
    Ale
    -0.07
    uştur
    -0.06
     υπηρε
    -0.06
    suffix
    -0.06
     UNIVERSITY
    -0.06
    (`<
    -0.06
    Luke
    -0.06
    POSITIVE LOGITS
     legend
    0.07
     collaborated
    0.07
    -related
    0.06
    -desc
    0.06
     Ground
    0.06
    )frame
    0.06
    _other
    0.06
    yu
    0.06
     neutral
    0.06
    彩
    0.06
    Act Density 0.025%

    No Known Activations