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

    Neuronpedia

    INDEX
    Explanations

    terms related to swords and similar weapons

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

    bladed weapons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     any
    -0.52
     aikana
    -0.44
    任何
    -0.43
    Any
    -0.41
     anything
    -0.40
     cualquier
    -0.39
     annuel
    -0.39
    BATCH
    -0.38
     totul
    -0.38
     عج
    -0.37
    POSITIVE LOGITS
     sword
    1.31
     swords
    1.28
     Sword
    1.26
    Sword
    1.19
     Swords
    1.17
    sword
    1.14
     sabre
    1.13
     Saber
    1.09
     espada
    1.04
    Saber
    1.04
    Act Density 0.015%

    No Known Activations