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

    Neuronpedia

    INDEX
    Explanations

    Explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magnet
    -0.07
    Orders
    -0.06
     router
    -0.06
    .CREATE
    -0.06
     martyr
    -0.06
     scanned
    -0.06
     Accept
    -0.06
     advised
    -0.06
    .BadRequest
    -0.06
    Century
    -0.06
    POSITIVE LOGITS
    iyah
    0.08
    ‐'
    0.07
    YLE
    0.07
    Uses
    0.06
     fuss
    0.06
    :].
    0.06
    .:.:.
    0.06
    _BITMAP
    0.06
     bé
    0.06
     viên
    0.06
    Act Density 0.047%

    No Known Activations