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

    Neuronpedia

    INDEX
    Explanations

    parenthetical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isos
    0.50
     trellis
    0.49
     basis
    0.49
     gzip
    0.49
     dielectric
    0.48
     comet
    0.47
     merges
    0.47
     chessboard
    0.47
     ب
    0.47
     gauges
    0.47
    POSITIVE LOGITS
    There
    0.57
    ı
    0.51
    <h3>
    0.50
    Ми
    0.48
    there
    0.47
    While
    0.47
    Going
    0.47
    á
    0.47
    You
    0.45
    Пре
    0.45
    Act Density 0.038%

    No Known Activations