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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal issues and regulations

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

    followed by prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    verbs and verb forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -1.00
    tvguidetime
    -0.92
     "..\..\
    -0.88
     للاسماء
    -0.80
    DataAnnotations
    -0.76
     оригіналу
    -0.76
    iformis
    -0.75
    bootstrapcdn
    -0.75
    Демографія
    -0.74
     المعيارى
    -0.74
    POSITIVE LOGITS
    ings
    0.95
    ing
    0.94
    ingly
    0.80
    able
    0.71
    inge
    0.69
    fully
    0.69
    ded
    0.67
    in
    0.62
    ments
    0.60
    d
    0.57
    Act Density 0.594%

    No Known Activations