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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or dataset identifiers

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

    Single letters followed by a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    list element delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etheless
    -0.81
    éns
    -0.73
     APPRO
    -0.71
     awakeFromNib
    -0.67
    ')):
    -0.67
    "):
    -0.67
     PICTOGRAM
    -0.66
     atta
    -0.66
     vig
    -0.65
     senti
    -0.65
    POSITIVE LOGITS
    setP
    0.81
     Humanos
    0.80
     réguli
    0.78
     alluminio
    0.77
     S
    0.77
     uomini
    0.76
     bună
    0.76
    Przypisy
    0.75
     cottura
    0.74
     soldati
    0.74
    Act Density 1.737%

    No Known Activations