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

    Neuronpedia

    INDEX
    Explanations

    E-commerce identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    重大
    0.33
    న్నో
    0.30
    ិច
    0.30
     treble
    0.30
     ಅನೇಕ
    0.29
    ्रीट
    0.29
    킥
    0.29
     marginalised
    0.28
     pilota
    0.28
     SLOT
    0.28
    POSITIVE LOGITS
    D
    0.33
    Emb
    0.31
    fort
    0.30
    com
    0.29
    f
    0.29
    b
    0.29
    News
    0.29
    ---------------
    0.28
    V
    0.28
    be
    0.28
    Act Density 0.006%

    No Known Activations