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

    Neuronpedia

    INDEX
    Explanations

    programming arguments and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Situ
    0.79
    .$\
    0.77
     Слу
    0.77
     Mean
    0.77
     DOI
    0.76
     MEAN
    0.76
     Symbol
    0.75
     glLight
    0.73
     상
    0.73
     CUDA
    0.73
    POSITIVE LOGITS
    args
    1.51
    arg
    1.37
    obj
    1.24
    data
    1.20
     args
    1.19
    input
    1.17
    target
    1.14
     _)
    1.12
    params
    1.12
    event
    1.10
    Act Density 0.205%

    No Known Activations