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

    Neuronpedia

    INDEX
    Explanations

    actions related to everyday activities and interactions

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

    followed by a verb form ending in "-ing"

    np_acts-logits-general · gemini-2.0-flash

    verbs describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estimés
    -0.79
     MainAxisSize
    -0.70
    สึก
    -0.60
    NUMX
    -0.59
    ionados
    -0.57
    arised
    -0.57
    ConstraintMaker
    -0.57
    ceedings
    -0.57
    Filmographie
    -0.55
    Šaltiniai
    -0.55
    POSITIVE LOGITS
     stuff
    0.63
     ویکی‌پدی
    0.61
     allerlei
    0.52
    astéroïdes
    0.52
    while
    0.50
    stuff
    0.50
     desperately
    0.49
     béné
    0.49
    OrNil
    0.49
     various
    0.49
    Act Density 0.284%

    No Known Activations