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

    Neuronpedia

    INDEX
    Explanations

    such / specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这是
    0.71
     ovaj
    0.71
    這是
    0.70
    놔
    0.70
     נישט
    0.70
     almeno
    0.69
     questo
    0.67
    ましたが
    0.67
     রাতে
    0.67
     చిత్ర
    0.67
    POSITIVE LOGITS
     such
    1.21
    such
    1.19
     thereof
    1.17
     sådan
    1.14
    Such
    1.14
     тако
    1.11
     Such
    1.09
     그런
    1.07
    そのような
    1.05
     therein
    1.03
    Act Density 0.271%

    No Known Activations