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

    Neuronpedia

    INDEX
    Explanations

    references to computer viruses and system configurations

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

    happening again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alça
    -0.41
    RTGC
    -0.41
     Monfieur
    -0.40
     Meksi
    -0.40
     torebka
    -0.40
     médicale
    -0.40
     sukienka
    -0.40
     ExecuteAsync
    -0.40
     Consultez
    -0.39
     faldas
    -0.37
    POSITIVE LOGITS
    twimg
    0.58
    principalColumn
    0.56
     nahilalakip
    0.45
     ویکی‌پدی
    0.42
     Réponses
    0.41
     Италијани
    0.41
     wireType
    0.40
     re
    0.40
    лтамалар
    0.39
    SizeMode
    0.39
    Act Density 0.057%

    No Known Activations