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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     railway
    -0.10
    ict
    -0.09
    铁路
    -0.08
     מתאים
    -0.08
    Uris
    -0.07
     cranes
    -0.07
     Clermont
    -0.07
    istar
    -0.07
     confidently
    -0.07
    ium
    -0.07
    POSITIVE LOGITS
     retali
    0.10
     Combat
    0.10
     玩家
    0.10
    玩家
    0.10
     potion
    0.10
    Enemies
    0.10
     retaliation
    0.10
     Allies
    0.09
     Fighters
    0.09
    .enemy
    0.09
    Act Density 0.004%

    No Known Activations