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

    Neuronpedia

    INDEX
    Explanations

    enemies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tariff
    -0.09
     tarif
    -0.08
     tunt
    -0.08
    Foods
    -0.08
     Css
    -0.07
     actuator
    -0.07
     facteur
    -0.07
     acidity
    -0.07
     factor
    -0.07
     Foods
    -0.07
    POSITIVE LOGITS
    .enemy
    0.09
     clustered
    0.09
     defeated
    0.09
     погиб
    0.09
     নিহত
    0.09
     विजय
    0.09
     statues
    0.09
    .hero
    0.09
     abandoned
    0.08
     வீர
    0.08
    Act Density 0.003%

    No Known Activations