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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters like slashes and dashes

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

    dates with separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.58
     myſelf
    -0.48
     Italijani
    -0.47
     ProtoMessage
    -0.47
     Италијани
    -0.45
     useAppContext
    -0.45
    Descripció
    -0.45
     Anſ
    -0.45
     Мексичка
    -0.44
    новништво
    -0.43
    POSITIVE LOGITS
     September
    0.61
     March
    0.57
     October
    0.57
     February
    0.57
     April
    0.56
     week
    0.56
     December
    0.56
     January
    0.56
     November
    0.56
     July
    0.55
    Act Density 0.011%

    No Known Activations