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

    Neuronpedia

    INDEX
    Explanations

    numerical data and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical/scientific negative values

    np_acts-logits-general · gemini-2.0-flash

    mathematical intervals and negative numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Appel
    -0.44
     wh
    -0.44
    pl
    -0.42
     شنا
    -0.41
     plural
    -0.41
     magn
    -0.41
    ladas
    -0.40
     kommen
    -0.40
    Mag
    -0.39
    wh
    -0.39
    POSITIVE LOGITS
     (-
    1.17
    (-
    1.16
     negative
    1.11
     [-
    1.04
     negatif
    1.00
     $(-
    1.00
     $-
    0.99
     (−
    0.99
    Negative
    0.95
    negative
    0.94
    Act Density 0.938%

    No Known Activations