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

    Neuronpedia

    INDEX
    Explanations

    UML diagrams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sume
    -0.07
    之一
    -0.07
    キー
    -0.07
    _xml
    -0.07
    чества
    -0.06
    ow
    -0.06
     domain
    -0.06
    兩
    -0.06
    :date
    -0.06
    �江
    -0.06
    POSITIVE LOGITS
     verbose
    0.07
    <bool
    0.07
     लग
    0.06
    _beta
    0.06
     pelvic
    0.06
     getSupportActionBar
    0.06
     строк
    0.06
     Scot
    0.06
     Upgrade
    0.06
    机会
    0.06
    Act Density 0.061%

    No Known Activations