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

    Neuronpedia

    INDEX
    Explanations

    column definitions and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蛉
    0.44
     ხოლო
    0.44
     دوبارہ
    0.42
     során
    0.42
    ัตว์
    0.41
     marquées
    0.41
     isti
    0.41
     ഇന്ന്
    0.40
     fertilized
    0.40
    enderal
    0.40
    POSITIVE LOGITS
    â
    0.45
     Th
    0.44
    thumbnail
    0.44
     Byte
    0.43
    nullable
    0.42
    Bytes
    0.42
     Optim
    0.40
     An
    0.39
    byte
    0.39
    A
    0.39
    Act Density 0.006%

    No Known Activations