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

    Neuronpedia

    INDEX
    Explanations

    Getting Things Done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.45
    色
    0.42
     glorify
    0.42
    ロー
    0.39
     May
    0.38
    蒔
    0.38
    概念
    0.38
     setters
    0.37
    配布
    0.37
     stated
    0.36
    POSITIVE LOGITS
    幄
    0.46
    बूझ
    0.44
    iteiten
    0.44
    europa
    0.43
     grandeza
    0.42
     가지고
    0.42
    胯
    0.42
    iliśmy
    0.42
     Europa
    0.42
     أوروبا
    0.41
    Act Density 0.002%

    No Known Activations