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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to functions and mechanics in technical or scientific contexts

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

    Mathematical or physics equations/formulas

    np_acts-logits-general · gemini-2.0-flash

    velocity or speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.63
     }{@
    -0.58
     bis
    -0.55
     filter
    -0.55
     filters
    -0.53
    agaimana
    -0.52
    Entrevista
    -0.51
     membership
    -0.51
    RESH
    -0.50
     kanal
    -0.50
    POSITIVE LOGITS
     religieuses
    0.65
     domestiques
    0.61
     ioutil
    0.61
     religiosas
    0.61
     religieux
    0.56
     domestique
    0.56
     Syrie
    0.55
     Moslem
    0.55
     casero
    0.54
     MonoBehaviour
    0.54
    Act Density 0.438%

    No Known Activations