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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è®°èĢħ
    -0.27
    毡
    -0.26
    Abs
    -0.26
     proportion
    -0.25
     univers
    -0.24
    å¯Įè´µ
    -0.24
    cope
    -0.24
    itz
    -0.24
     Bir
    -0.24
    Press
    -0.23
    POSITIVE LOGITS
     parti
    0.28
    ogie
    0.27
    oints
    0.26
    ç»ĵ
    0.25
    ä¼ļéķ¿
    0.25
    hap
    0.24
    ogy
    0.24
    uhan
    0.24
    .dy
    0.23
     wards
    0.23
    Act Density 1.395%

    No Known Activations