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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suppressed
    -0.07
    $rows
    -0.06
    STATUS
    -0.06
    TEMP
    -0.06
     airs
    -0.06
     deport
    -0.06
    (docs
    -0.06
     shifted
    -0.06
     jails
    -0.06
    film
    -0.06
    POSITIVE LOGITS
    Triple
    0.07
     Bliss
    0.07
     BLACK
    0.07
     Gn
    0.07
    _comm
    0.06
    Tech
    0.06
     PY
    0.06
    .sprites
    0.06
    .setScene
    0.06
     Kits
    0.06
    Act Density 0.003%

    No Known Activations