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

    Neuronpedia

    INDEX
    Explanations

    things to consider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.53
    /
    0.53
    .
    0.49
    gia
    0.47
    ,
    0.47
    "
    0.46
    ?
    0.46
    !
    0.46
     PI
    0.45
     M
    0.45
    POSITIVE LOGITS
    🍘
    0.52
    ๅ
    0.49
     पनि
    0.47
    ਾਮ
    0.45
     丿
    0.45
    萧
    0.45
    ंजय
    0.44
     सितारों
    0.44
     ै
    0.44
    Ҷ
    0.44
    Act Density 0.001%

    No Known Activations