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

    Neuronpedia

    INDEX
    Explanations

    specific terminology related to science and technology

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

    functional descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.65
    IUrlHelper
    -0.58
    NameInMap
    -0.57
    Демографія
    -0.57
     gynhyrchwyd
    -0.54
    Diweddarwch
    -0.53
    OGND
    -0.52
     فريبيس
    -0.52
    Tembelea
    -0.50
     ब्रेकडाउन
    -0.49
    POSITIVE LOGITS
     also
    0.66
     arşivlendi
    0.47
    also
    0.41
     ayrıca
    0.41
     essentially
    0.41
     Also
    0.40
     همچنین
    0.40
     typically
    0.39
     currently
    0.39
    ResponseWriter
    0.39
    Act Density 0.063%

    No Known Activations