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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thoroughly
    -0.07
    error
    -0.07
     Сов
    -0.06
    _estimators
    -0.06
    (ignore
    -0.06
     refin
    -0.06
     corners
    -0.06
    夫
    -0.06
    CONTEXT
    -0.06
    :[[
    -0.06
    POSITIVE LOGITS
     NGC
    0.07
    활동
    0.06
     Armed
    0.06
        ↵    ↵    ↵
    0.06
     interconnected
    0.06
    _individual
    0.06
    !")
↵
    0.06
    xlim
    0.06
    'elle
    0.06
    AutoresizingMask
    0.06
    Act Density 0.005%

    No Known Activations