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

    Neuronpedia

    INDEX
    Explanations

    Chrome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Haz
    -0.07
    ང
    -0.06
    ғ
    -0.06
     Overnight
    -0.06
    ignored
    -0.06
     introduces
    -0.06
    言
    -0.06
     Grund
    -0.06
     Magnus
    -0.06
    errated
    -0.06
    POSITIVE LOGITS
     thriving
    0.07
    .Ab
    0.07
     plains
    0.07
    /do
    0.07
    ;');↵
    0.07
    副书记
    0.07
    _arg
    0.07
    就诊
    0.07
     "#"
    0.07
    _day
    0.07
    Act Density 0.001%

    No Known Activations