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

    Neuronpedia

    INDEX
    Explanations

    instances of underscores in text, likely indicating formatted or structured components

    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
     disambiguazione
    -0.84
    UnusedPrivate
    -0.84
     queſta
    -0.80
    EndContext
    -0.79
    istoitu
    -0.76
    parsedMessage
    -0.76
     estekak
    -0.75
     HasFactory
    -0.73
    Geplaatst
    -0.73
    expandindo
    -0.72
    POSITIVE LOGITS
    _
    0.58
     
    0.48
    ↵↵
    0.47
     câbles
    0.44
    ↵
    0.41
     grossly
    0.40
     natuurlijke
    0.36
      
    0.35
     relatively
    0.34
     uncer
    0.34
    Act Density 0.088%

    No Known Activations