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

    Neuronpedia

    INDEX
    Explanations

    The individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enemigo
    0.47
    Effect
    0.45
    Enemy
    0.45
    enemy
    0.40
    夥伴
    0.40
     enemy
    0.39
    Dish
    0.39
    浮か
    0.39
    Произ
    0.39
    大佬
    0.39
    POSITIVE LOGITS
     individual
    0.64
     individuals
    0.64
     individu
    0.59
     индивидуа
    0.57
     Individuals
    0.56
     individus
    0.56
     deceased
    0.54
     unidentified
    0.54
     unnamed
    0.54
     обстоятельства
    0.52
    Act Density 0.020%

    No Known Activations