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

    Neuronpedia

    INDEX
    Explanations

    statistics/deviation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .manual
    -0.08
    .Library
    -0.08
    ",'
    -0.07
    "↵
    -0.07
     smartphones
    -0.07
    )"↵
    -0.07
     sympath
    -0.07
     વાર
    -0.07
     coverage
    -0.07
    .Virtual
    -0.07
    POSITIVE LOGITS
    レス
    0.08
    ändert
    0.08
     svar
    0.08
     prestige
    0.08
    ինի
    0.08
     wurdt
    0.08
    (sizeof
    0.08
    Array
    0.08
     prestigious
    0.08
    ంద్ర
    0.08
    Act Density 0.006%

    No Known Activations