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

    Neuronpedia

    INDEX
    Explanations

    communicating updates to you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Enumer
    0.44
     Supplementary
    0.43
     Elimin
    0.42
    assignmentItems
    0.42
     equalization
    0.42
    ត្ត
    0.42
     srcs
    0.41
     ควร
    0.40
     elongation
    0.40
     Explanation
    0.40
    POSITIVE LOGITS
    Dog
    0.43
    Madison
    0.43
    В
    0.42
    When
    0.41
    Who
    0.41
    ма
    0.41
    Where
    0.40
    Notify
    0.40
    в
    0.40
    car
    0.40
    Act Density 0.001%

    No Known Activations