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

    Neuronpedia

    INDEX
    Explanations

    references to mistakes and errors

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

    errors or mistakes

    np_acts-logits-general · gemini-2.0-flash

    mistakes and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pecto
    -0.44
     الجد
    -0.43
     للمعارف
    -0.43
     oprot
    -0.41
    EncBinary
    -0.41
     الشع
    -0.41
    enforce
    -0.40
     Dostupné
    -0.40
     harten
    -0.40
    cillor
    -0.40
    POSITIVE LOGITS
     mistakes
    1.30
     Mistakes
    1.20
     errors
    1.13
     mistake
    1.13
     Fehler
    1.12
     defects
    1.10
     faults
    1.09
     Errors
    1.06
     Defects
    1.02
     defect
    0.99
    Act Density 0.467%

    No Known Activations