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

    Neuronpedia

    INDEX
    Explanations

    If you were a vegetable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    го
    0.45
    е
    0.44
     transacción
    0.43
    drinking
    0.43
    су
    0.42
    ってる
    0.42
    killed
    0.41
    uber
    0.41
    лимпий
    0.41
     одного
    0.40
    POSITIVE LOGITS
     akadem
    0.42
     오늘
    0.42
     प्रकल्प
    0.41
     निघ
    0.40
    指导
    0.40
     Hungarian
    0.40
     sejarah
    0.40
    Dise
    0.40
     izdel
    0.40
    他说
    0.39
    Act Density 0.002%

    No Known Activations