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

    Neuronpedia

    INDEX
    Explanations

    slow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¸Ĥåľºä¸Ĭ
    -0.28
    åĨĴ
    -0.27
    èĥĮä¸Ĭ
    -0.27
     hum
    -0.27
    rus
    -0.25
    wear
    -0.25
    =$((
    -0.25
    maid
    -0.25
    eded
    -0.25
     (!((
    -0.25
    POSITIVE LOGITS
     Speakers
    0.29
    äch
    0.28
    anches
    0.27
     Quant
    0.26
     quantitative
    0.25
    quant
    0.25
     Convenient
    0.25
    aye
    0.25
    -dem
    0.24
     convenience
    0.24
    Act Density 0.043%

    No Known Activations