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

    Neuronpedia

    INDEX
    Explanations

    weapon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inkle
    -0.07
    [next
    -0.07
    тою
    -0.07
     Moore
    -0.07
    -0.06
     하루
    -0.06
     gives
    -0.06
     Mild
    -0.06
     DOC
    -0.06
     ilg
    -0.06
    POSITIVE LOGITS
     weapon
    0.12
     weapons
    0.10
    weapons
    0.09
    Weapons
    0.08
    .weapon
    0.08
     Weapon
    0.08
    Weapon
    0.07
    ，被
    0.07
     weaponry
    0.07
     Weapons
    0.07
    Act Density 0.007%

    No Known Activations