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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ủng
    -0.07
    为了避免
    -0.06
    may
    -0.06
     plaisir
    -0.06
    (slot
    -0.06
    哪些
    -0.06
    pl
    -0.06
    Similar
    -0.06
    -shirt
    -0.06
    żeli
    -0.06
    POSITIVE LOGITS
     Loads
    0.07
     utc
    0.07
    嵚
    0.07
     venom
    0.07
    (sound
    0.07
    ('.')[
    0.07
     ATA
    0.07
     emlrt
    0.07
    .speed
    0.07
     Dame
    0.07
    Act Density 0.012%

    No Known Activations