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

    Neuronpedia

    INDEX
    Explanations

    order and position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    俯
    0.50
     وسط
    0.45
    centerX
    0.45
    Downtown
    0.44
     across
    0.44
    Within
    0.44
     riverside
    0.43
     inland
    0.43
     ángulo
    0.43
    Didn
    0.43
    POSITIVE LOGITS
     항상
    0.46
    zné
    0.46
     topological
    0.44
     preferably
    0.44
     STRICT
    0.43
    চী
    0.42
     estrict
    0.42
     dfs
    0.42
     lexical
    0.42
     まあ
    0.41
    Act Density 0.013%

    No Known Activations