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

    Neuronpedia

    INDEX
    Explanations

    News agencies and publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    積
    -0.07
    -density
    -0.07
    categories
    -0.07
     tolerance
    -0.07
    (targetEntity
    -0.07
    .prod
    -0.06
    density
    -0.06
     марш
    -0.06
    _density
    -0.06
     Reeves
    -0.06
    POSITIVE LOGITS
    (Int
    0.07
    ALLOW
    0.07
     став
    0.06
    (moment
    0.06
    layout
    0.06
    '&&
    0.06
    _exit
    0.06
    іна
    0.06
    getView
    0.06
    YT
    0.06
    Act Density 0.024%

    No Known Activations