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

    Neuronpedia

    INDEX
    Explanations

    strategy and combat effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     географи
    0.97
    industrie
    0.96
     certificado
    0.95
     පරි
    0.95
    OECD
    0.93
    aménagement
    0.92
     polynucle
    0.92
    零部件
    0.92
     questionnaire
    0.90
    域名
    0.90
    POSITIVE LOGITS
     attacks
    2.02
     attack
    1.99
     weapon
    1.89
     enemy
    1.89
     weapons
    1.83
     attackers
    1.78
     melee
    1.76
     attacking
    1.75
     Attacks
    1.72
     Attack
    1.71
    Act Density 0.336%

    No Known Activations