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

    Neuronpedia

    INDEX
    Explanations

    instances of measurement or statistical data

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

    numbers preceding abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Numerade
    -0.66
     queſta
    -0.66
    GraphicsUnit
    -0.65
     desmotivaciones
    -0.64
    Демографія
    -0.60
    (©
    -0.59
    AndEndTag
    -0.59
     ſeveral
    -0.58
     houſe
    -0.58
     Paglinawan
    -0.57
    POSITIVE LOGITS
     &
    0.53
    TR
    0.46
    SM
    0.45
    &
    0.44
       
    0.44
           
    0.44
    javax
    0.44
     \
    0.43
    ML
    0.43
    quad
    0.42
    Act Density 0.043%

    No Known Activations