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

    Neuronpedia

    INDEX
    Explanations

    instances of structured formatting or special symbols in text

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

    numeric sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.49
    цездатний
    -0.41
    ionalmente
    -0.40
    حياته
    -0.38
     ویکی‌پدی
    -0.38
     abundante
    -0.38
     baskılı
    -0.37
     citazioni
    -0.35
     itinéraires
    -0.35
    éez
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.50
    ########.
    0.49
    hyrchwyd
    0.47
     MainAxisSize
    0.47
    RTLR
    0.46
    tonode
    0.46
     tramonto
    0.46
    protoimpl
    0.45
     AssemblyProduct
    0.44
    AndEndTag
    0.44
    Act Density 0.017%

    No Known Activations