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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize importance or centrality within a context

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

    Preceding "point," "extent," or "exclusion."

    np_acts-logits-general · gemini-2.0-flash

    phrases of degree or limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aikana
    -0.56
     Gelegenheit
    -0.52
     мол
    -0.50
     handen
    -0.49
     jäsen
    -0.48
     Absicht
    -0.48
     attravers
    -0.45
     initComponents
    -0.45
     elämä
    -0.43
     aufges
    -0.42
    POSITIVE LOGITS
     extent
    1.77
    extent
    1.29
     detriment
    1.27
     degree
    1.27
     point
    1.18
     tune
    1.11
     fullest
    1.11
     Extent
    1.08
     chagrin
    0.95
     hilt
    0.94
    Act Density 0.193%

    No Known Activations