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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kob
    -0.06
    鬼
    -0.06
    _bot
    -0.06
    _head
    -0.06
    社
    -0.06
    _LOADED
    -0.06
     эф
    -0.06
     disco
    -0.06
     ppt
    -0.06
    Spanish
    -0.06
    POSITIVE LOGITS
     ва
    0.07
    ──
    0.07
    кас
    0.07
    +='
    0.06
    <Image
    0.06
    .findAll
    0.06
    manufacturer
    0.06
    .authorization
    0.06
    .view
    0.06
    WL
    0.06
    Act Density 0.012%

    No Known Activations