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

    Neuronpedia

    INDEX
    Explanations

    terms related to the omission or exclusion of elements or information

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

    omitting or withholding elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itulah
    -0.48
     Stur
    -0.44
     Đường
    -0.44
     tremp
    -0.43
     debout
    -0.42
     pneus
    -0.41
    GraphicsUnit
    -0.40
     orina
    -0.40
     líqu
    -0.40
     وأن
    -0.40
    POSITIVE LOGITS
     omission
    0.68
     omit
    0.66
     withholding
    0.59
     withhold
    0.59
     spared
    0.59
     withheld
    0.58
     omitting
    0.58
     betweenstory
    0.57
     omitted
    0.56
    omit
    0.56
    Act Density 0.025%

    No Known Activations