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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and events

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

    historical figures and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.57
    posal
    -0.49
     للاسماء
    -0.46
     Moha
    -0.44
     mohair
    -0.43
    querque
    -0.43
    ception
    -0.43
    mello
    -0.42
     apostolic
    -0.41
    obium
    -0.41
    POSITIVE LOGITS
     AttributeSet
    0.52
     marbre
    0.46
     griego
    0.44
    GMENT
    0.43
     informée
    0.42
     forhold
    0.42
     leçons
    0.40
     étrangers
    0.40
     púrpura
    0.40
     personnelle
    0.39
    Act Density 0.019%

    No Known Activations