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

    Neuronpedia

    INDEX
    Explanations

    specific structured elements and formatting in technical or scientific texts

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

    et al. citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.69
     <>",
    -0.66
     ModelRenderer
    -0.65
     abstrait
    -0.64
     saveiro
    -0.64
     收納
    -0.62
     doInBackground
    -0.61
     queſta
    -0.60
    parsedMessage
    -0.60
     desmotivaciones
    -0.59
    POSITIVE LOGITS
    CloseOperation
    0.36
    
    0.35
     official
    0.33
    FlatStyle
    0.32
     Official
    0.31
     Dez
    0.31
     mit
    0.30
     Drapeau
    0.30
    '
    0.29
     MOD
    0.29
    Act Density 0.036%

    No Known Activations