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

    Neuronpedia

    INDEX
    Explanations

    damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itinerary
    -0.09
     whereabouts
    -0.08
    -access
    -0.08
     Ode
    -0.08
    wrapper
    -0.08
     agenda
    -0.08
     vì
    -0.07
    _wrapper
    -0.07
    (Uri
    -0.07
    -wrapper
    -0.07
    POSITIVE LOGITS
    	damage
    0.15
     damage
    0.15
    .damage
    0.14
    damage
    0.14
    Damage
    0.14
     DAMAGE
    0.14
    _damage
    0.14
     Damage
    0.13
     melee
    0.13
    攻击
    0.13
    Act Density 0.013%

    No Known Activations