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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LoggerFactory
    -0.07
    azı
    -0.07
    (ver
    -0.07
     Yong
    -0.06
    vester
    -0.06
    -random
    -0.06
    letes
    -0.06
    ackages
    -0.06
    /rand
    -0.06
     æ
    -0.06
    POSITIVE LOGITS
     accelerate
    0.07
    $item
    0.07
    <nav
    0.06
    increase
    0.06
    遭
    0.06
     steals
    0.06
     unknow
    0.06
    ???
    0.06
    Collider
    0.06
     :]
    0.06
    Act Density 0.041%

    No Known Activations