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

    Neuronpedia

    INDEX
    Explanations

    UI elements and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िकेशन
    0.38
     autón
    0.37
    getNumber
    0.37
     phiên
    0.36
     AsyncStorage
    0.36
     GEAR
    0.35
     câmera
    0.35
    ینګ
    0.34
     playGame
    0.34
    )[
    0.34
    POSITIVE LOGITS
    -
    0.59
    class
    0.48
    _
    0.46
     клас
    0.45
    Class
    0.44
     класс
    0.44
     class
    0.43
    Reader
    0.41
    essel
    0.39
    TableCell
    0.39
    Act Density 0.003%

    No Known Activations