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

    Neuronpedia

    INDEX
    Explanations

    code or fill blanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    சரி
    0.49
     doesn
    0.47
    ยาน
    0.44
     or
    0.43
     understands
    0.43
    ாலின்
    0.43
     understand
    0.42
     whim
    0.41
    egin
    0.41
     lets
    0.40
    POSITIVE LOGITS
    ributedString
    0.50
     wobei
    0.45
     Breeder
    0.45
    aryng
    0.44
    лий
    0.43
     với
    0.43
     Distillery
    0.43
    VIAF
    0.43
    سطس
    0.42
     &[
    0.42
    Act Density 0.003%

    No Known Activations