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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hasattr
    -0.08
    诚信
    -0.08
    対象
    -0.08
     tanah
    -0.08
    очным
    -0.08
     prud
    -0.07
    _domain
    -0.07
    (data
    -0.07
     domain
    -0.07
     dikk
    -0.07
    POSITIVE LOGITS
     모습
    0.09
     પ્રવ
    0.09
     típico
    0.09
     journée
    0.09
     rotina
    0.09
     જીવન
    0.09
    一天
    0.09
     cotidiano
    0.09
     sehari
    0.09
     giornata
    0.09
    Act Density 0.017%

    No Known Activations