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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or topics

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

    "this" followed by punctuation or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نمای
    -0.44
     Tunisian
    -0.43
    writerow
    -0.43
     Belgian
    -0.41
     filter
    -0.39
     Venezuelan
    -0.39
     claw
    -0.39
     receive
    -0.39
     Mme
    -0.39
    erapeu
    -0.38
    POSITIVE LOGITS
     sowas
    0.48
     noqa
    0.48
     ProtoMessage
    0.46
     charité
    0.46
    itself
    0.46
     trône
    0.43
     avenir
    0.43
     remplissage
    0.41
     bonté
    0.41
     NavController
    0.41
    Act Density 0.097%

    No Known Activations