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

    Neuronpedia

    INDEX
    Explanations

    details related to weapons, specifically swords and knives

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

    knives or sharp objects

    np_acts-logits-general · gemini-2.0-flash

    sharp knife or blade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.73
     EconPapers
    -0.59
    żesz
    -0.59
     referenties
    -0.57
     Bullock
    -0.56
    épendance
    -0.52
    Cyfeiriadau
    -0.52
    hoots
    -0.52
     Soares
    -0.52
     виправивши
    -0.51
    POSITIVE LOGITS
     blade
    1.44
     knife
    1.30
     blades
    1.26
     knives
    1.22
     Blade
    1.21
    Blade
    1.19
    blade
    1.14
     Knife
    1.13
    Knife
    1.10
     Blades
    1.09
    Act Density 0.127%

    No Known Activations