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

    Neuronpedia

    INDEX
    Explanations

    advantage or winning chess and sports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invern
    0.75
    元年
    0.72
     monatomic
    0.70
    ATIONS
    0.67
    nsan
    0.67
    融入
    0.66
    attoos
    0.66
     dissoci
    0.65
    jeto
    0.65
    हद
    0.64
    POSITIVE LOGITS
     advantage
    1.47
     ventaja
    1.33
     vantagem
    1.29
    advantage
    1.24
     disadvantage
    1.21
     Advantage
    1.20
    优势
    1.20
     stalemate
    1.18
     advantages
    1.17
     vantaggio
    1.15
    Act Density 0.177%

    No Known Activations