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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific measurements and calculations in physics

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

    Mathematical/scientific terminology

    np_acts-logits-general · gemini-2.0-flash

    physical and mathematical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.73
     صوتيه
    -0.68
     hebdomada
    -0.64
    Personensuche
    -0.63
     transfieras
    -0.60
     GenerationType
    -0.60
    تقاوى
    -0.59
    ########.
    -0.57
    🏻‍♀️
    -0.55
    iosamente
    -0.54
    POSITIVE LOGITS
     probed
    0.69
     near
    0.67
     around
    0.61
     inside
    0.59
     away
    0.58
     induced
    0.56
     governed
    0.56
     parametri
    0.56
     corresponding
    0.54
     nahe
    0.52
    Act Density 2.177%

    No Known Activations