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

    Neuronpedia

    INDEX
    Explanations

    goals and achieving them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用法
    0.35
    adies
    0.35
     leven
    0.34
    muje
    0.34
    اريات
    0.34
     церкви
    0.32
     परख
    0.31
    ங்குகள்
    0.31
     insisting
    0.31
     bety
    0.31
    POSITIVE LOGITS
     goals
    3.97
     goal
    3.88
     목표
    3.59
     Goals
    3.58
    goal
    3.56
    goals
    3.50
    Goals
    3.47
    目標
    3.44
    Goal
    3.41
     Goal
    3.38
    Act Density 0.248%

    No Known Activations