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

    Neuronpedia

    INDEX
    Explanations

    various types of weapons and combat-related terminology

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

    weapons or tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.49
     svar
    -0.38
    JsonHelper
    -0.38
    ╗
    -0.37
    posables
    -0.36
    definecolor
    -0.33
    封
    -0.31
    ぼ
    -0.30
     MonoBehaviour
    -0.29
    eddah
    -0.29
    POSITIVE LOGITS
     sword
    0.63
     swords
    0.61
     brooms
    0.60
    Cane
    0.60
     machete
    0.58
     kılı
    0.56
     broom
    0.56
    sword
    0.55
     swung
    0.54
    instrument
    0.54
    Act Density 0.090%

    No Known Activations