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

    Neuronpedia

    INDEX
    Explanations

    translate this/these into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    するのは
    0.46
    三個
    0.44
     trzech
    0.43
    three
    0.42
     பத்து
    0.40
     तीन
    0.40
    THREE
    0.40
     tři
    0.40
     trzy
    0.39
     ಪ್ರಯೋಜನ
    0.39
    POSITIVE LOGITS
     sentences
    0.71
    这句话
    0.68
     phrases
    0.67
     these
    0.64
     sentence
    0.60
     frases
    0.60
     phrase
    0.59
    句子
    0.59
    这段
    0.58
     frase
    0.57
    Act Density 0.046%

    No Known Activations