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

    Neuronpedia

    INDEX
    Explanations

    references to firearms or weapons

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

    guns or gun-related actions

    np_acts-logits-general · gemini-2.0-flash

    wielding guns and swords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.55
     venuto
    -0.52
    ✨:
    -0.51
     Schia
    -0.51
     verkla
    -0.49
    mapStateToProps
    -0.49
    liction
    -0.49
    rapnel
    -0.49
     Castle
    -0.49
     Injectable
    -0.49
    POSITIVE LOGITS
     wielded
    0.79
     bearer
    0.73
     Bearer
    0.68
    bearer
    0.67
     bearers
    0.64
     wiel
    0.63
     handle
    0.62
     wield
    0.62
     held
    0.61
     holder
    0.60
    Act Density 0.252%

    No Known Activations