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

    Neuronpedia

    INDEX
    Explanations

    URLs with IDs and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.22
    ’
    0.22
     (
    0.21
     non
    0.20
    BT
    0.19
    (-
    0.18
    '
    0.17
    ,
    0.17
    *
    0.17
     being
    0.17
    POSITIVE LOGITS
    ăpadă
    0.25
    त्रेयी
    0.24
    𒈹
    0.24
    <unused309>
    0.24
    mataspid
    0.23
    jiwarl
    0.23
     Pogis
    0.23
     sasan
    0.23
    ગાહી
    0.23
    𒁍
    0.23
    Act Density 0.065%

    No Known Activations