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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

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

    family, names, places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.91
     مرئيه
    -0.88
     يتيمه
    -0.85
    BeginContext
    -0.80
    tagHelperRunner
    -0.77
     otomatig
    -0.76
     CreateTagHelper
    -0.75
    MLLoader
    -0.75
     تضيفلها
    -0.73
     ModelExpression
    -0.71
    POSITIVE LOGITS
    Carriera
    0.38
     pecho
    0.35
    oczes
    0.35
     past
    0.32
     piernas
    0.31
    niów
    0.29
     what
    0.29
     dress
    0.29
     course
    0.29
     last
    0.27
    Act Density 0.153%

    No Known Activations