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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation symbols

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    戬
    -0.47
     AssemblyTitle
    -0.44
     Küste
    -0.43
    hyrchwyd
    -0.42
    atrician
    -0.40
     miniaturka
    -0.40
     cielos
    -0.39
     Sprache
    -0.39
     hâte
    -0.38
    раздо
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.55
    ValueStyle
    0.52
    ChildScrollView
    0.49
     فرا
    0.48
     DMS
    0.47
    arraycopy
    0.44
    sizeCache
    0.42
    ores
    0.42
     Storage
    0.42
     تعدى
    0.42
    Act Density 0.004%

    No Known Activations