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
    wheel
    -0.08
     heures
    -0.07
     diver
    -0.07
     kidd
    -0.06
    krét
    -0.06
     seaw
    -0.06
     Everett
    -0.06
     freeway
    -0.06
     gratuite
    -0.06
    ưa
    -0.06
    POSITIVE LOGITS
     damage
    0.13
     Damage
    0.11
    damage
    0.09
     damaged
    0.08
    Damage
    0.08
     damages
    0.07
     Samsung
    0.07
    μα
    0.07
     مجلس
    0.07
     DAMAGE
    0.07
    Act Density 0.018%

    No Known Activations