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

    Neuronpedia

    INDEX
    Explanations

    Impracticality or infeasibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obligaciones
    -0.08
     globalization
    -0.08
     패
    -0.08
     추
    -0.08
    별
    -0.08
     Kot
    -0.07
    今年
    -0.07
    cov
    -0.07
     기간
    -0.07
     ub
    -0.07
    POSITIVE LOGITS
     sprayed
    0.12
     explosives
    0.12
     incendi
    0.11
     engineered
    0.11
     muzzle
    0.11
     methane
    0.11
     aerosol
    0.11
    Projectile
    0.11
     nozzle
    0.11
    Weapons
    0.10
    Act Density 0.014%

    No Known Activations