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

    Neuronpedia

    INDEX
    Explanations

    instances of error handling in code

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

    code completion or return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.71
     estekak
    -0.65
     nahilalakip
    -0.63
    GEBURTSDATUM
    -0.62
     Italijanski
    -0.62
    Autoritní
    -0.62
     CreateTagHelper
    -0.60
     disambiguazione
    -0.59
    
    -0.59
     autorytatywna
    -0.59
    POSITIVE LOGITS
     Tropical
    0.32
     Trot
    0.30
    及
    0.29
    extrémité
    0.29
     Espec
    0.29
     diputados
    0.29
     Trop
    0.29
    Fatalf
    0.29
    ric
    0.28
    हीं
    0.28
    Act Density 0.008%

    No Known Activations