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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以用
    0.40
     membranes
    0.38
    spi
    0.37
    ChatItem
    0.37
     można
    0.37
    可以通过
    0.36
     możesz
    0.36
    memory
    0.35
    各类
    0.35
     pike
    0.35
    POSITIVE LOGITS
    วรร
    0.46
     Maximilian
    0.44
     Tết
    0.43
    ила
    0.42
     Ferdinand
    0.42
     безу
    0.41
     lastly
    0.41
    ✞
    0.41
     ...(
    0.41
     ର
    0.41
    Act Density 0.002%

    No Known Activations