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

    Neuronpedia

    INDEX
    Explanations

    loader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Palest
    -0.07
     Square
    -0.07
    anguage
    -0.07
     City
    -0.07
    isiert
    -0.07
     Králové
    -0.07
     MILF
    -0.06
    retch
    -0.06
     Raq
    -0.06
     Vaccine
    -0.06
    POSITIVE LOGITS
    dere
    0.08
    农
    0.07
    _calls
    0.07
     lear
    0.07
    �
    0.07
    (reordered
    0.06
    <!--<
    0.06
    fore
    0.06
    cookies
    0.06
    .transform
    0.06
    Act Density 0.002%

    No Known Activations