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

    Neuronpedia

    INDEX
    Explanations

    volume, part, episode, chapter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.52
    -
    0.51
     To
    0.50
    ,
    0.46
     From
    0.46
    (
    0.44
    /
    0.44
    |
    0.43
     in
    0.41
     at
    0.41
    POSITIVE LOGITS
    chyné
    0.57
     två
    0.55
    𒉣
    0.54
    jiwarl
    0.54
    ករណ៍
    0.53
    क्लेव
    0.52
     zwei
    0.51
    赭
    0.51
    राजनी
    0.50
    𒋛
    0.50
    Act Density 0.000%

    No Known Activations