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

    Neuronpedia

    INDEX
    Explanations

    Fight scenes descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    购
    -0.10
    wifi
    -0.08
    Wifi
    -0.08
    验
    -0.08
     someday
    -0.08
    厕所
    -0.08
     evenings
    -0.08
    Worksheet
    -0.08
    票
    -0.08
    trä
    -0.08
    POSITIVE LOGITS
    .attack
    0.13
     공격
    0.13
    攻击
    0.13
     melee
    0.13
     ആക്രമ
    0.13
     हमला
    0.12
     retali
    0.12
     opponent
    0.12
     attacking
    0.12
     saldır
    0.12
    Act Density 0.027%

    No Known Activations