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

    Neuronpedia

    INDEX
    Explanations

    references to knives or cutting instruments

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

    knife and its uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Greet
    -0.48
     Easter
    -0.47
     Eas
    -0.47
     Els
    -0.46
     Beal
    -0.46
     Anand
    -0.46
     Erb
    -0.45
     Popp
    -0.45
     Urqu
    -0.45
    PAC
    -0.45
    POSITIVE LOGITS
     knife
    2.16
     Knife
    2.06
    Knife
    2.06
    knife
    1.99
     knives
    1.77
     Knives
    1.67
     couteau
    1.55
     cuchillo
    1.46
    Kni
    1.31
    刀
    1.13
    Act Density 0.004%

    No Known Activations