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

    Neuronpedia

    INDEX
    Explanations

    bladed weapons like swords and knives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     checksum
    0.73
    嬪
    0.73
    aitre
    0.70
    藻
    0.70
    etet
    0.69
     Maternity
    0.68
    🎡
    0.68
    checksum
    0.68
     Telecom
    0.67
     Dots
    0.67
    POSITIVE LOGITS
     sword
    2.83
     weapons
    2.74
     knives
    2.67
     weapon
    2.66
     swords
    2.64
     knife
    2.61
     blade
    2.47
     weaponry
    2.41
     dagger
    2.36
     blades
    2.33
    Act Density 0.505%

    No Known Activations