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

    Neuronpedia

    INDEX
    Explanations

    setting goals and achieving them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strangely
    0.45
     antice
    0.43
     když
    0.42
    卷积
    0.41
     ጥቅም
    0.41
    注意事项
    0.40
    了一种
    0.40
    不如
    0.40
    选择了
    0.40
     bot
    0.40
    POSITIVE LOGITS
     목표
    1.18
    目標
    1.13
     goal
    1.09
     achieve
    1.06
    的目标
    1.06
     achieving
    1.05
    を目指
    1.03
     ambitious
    1.02
     goals
    1.01
    goal
    0.98
    Act Density 0.045%

    No Known Activations