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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     One
    -0.07
     based
    -0.06
    One
    -0.06
     Use
    -0.06
     exhaustive
    -0.06
    (Collectors
    -0.06
    _for
    -0.06
     ponds
    -0.06
    sparse
    -0.06
    gtest
    -0.06
    POSITIVE LOGITS
    ｰ
    0.07
     amer
    0.07
     λειτουργ
    0.06
    (QL
    0.06
    velle
    0.06
    olygon
    0.06
    unya
    0.06
     ки
    0.06
    (cancel
    0.06
    (optimizer
    0.06
    Act Density 0.013%

    No Known Activations