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

    Neuronpedia

    INDEX
    Explanations

    lists topics and following functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sadquotes
    0.30
     مزید
    0.30
     onDelete
    0.29
     schizophren
    0.29
     まず
    0.28
     stopwatch
    0.28
     दुसरे
    0.28
    悗
    0.28
     ऊपर
    0.28
     עם
    0.28
    POSITIVE LOGITS
    -
    0.46
    -,
    0.40
    /
    0.40
    im
    0.37
     themed
    0.33
    ,
    0.32
     Management
    0.31
    -(
    0.31
    related
    0.30
    ’
    0.30
    Act Density 0.361%

    No Known Activations