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

    Neuronpedia

    INDEX
    Explanations

    Associated Press news articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आँख
    0.52
    ूँ
    0.51
     Random
    0.50
    Towards
    0.50
     fucked
    0.50
    좆
    0.49
     Towards
    0.49
     Okay
    0.48
     NCBI
    0.48
     Mainland
    0.48
    POSITIVE LOGITS
    .___
    0.65
    AP
    0.62
     AP
    0.60
    ___
    0.59
     ___
    0.58
    एपी
    0.55
     রোববার
    0.53
     Associated
    0.50
     `'
    0.49
    蜜
    0.49
    Act Density 0.006%

    No Known Activations