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

    Neuronpedia

    INDEX
    Explanations

    left or right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    括号
    0.52
    యన్స్
    0.44
    Bracket
    0.44
    పు
    0.41
     bracket
    0.41
    柜
    0.41
    дентификаторы
    0.41
    괄
    0.40
    NSMutableArray
    0.40
    식회사
    0.40
    POSITIVE LOGITS
     left
    0.50
    left
    0.48
    ivas
    0.46
    Left
    0.44
    左
    0.42
     Left
    0.42
     Nub
    0.42
     Schn
    0.39
     starvation
    0.39
    lov
    0.39
    Act Density 0.002%

    No Known Activations