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

    Neuronpedia

    INDEX
    Explanations

    code and numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _h
    -0.07
    POSITE
    -0.06
    hf
    -0.06
     Round
    -0.06
     BASE
    -0.06
    hem
    -0.06
     επα
    -0.06
    Jessica
    -0.06
    mod
    -0.06
    [_
    -0.06
    POSITIVE LOGITS
     barred
    0.06
    859
    0.06
     Marshall
    0.06
    ”，
    0.06
    (ui
    0.06
     Sala
    0.06
    ….
    0.06
    =all
    0.06
    …..
    0.06
     ','.
    0.06
    Act Density 0.327%

    No Known Activations