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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and diagrams

    oai_token-act-pair · gemini-2.0-flash

    mathematical diagrams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.77
     للمعارف
    -0.68
     kasarigan
    -0.68
    SharedCtor
    -0.68
    存于互联网档案馆
    -0.66
     referenties
    -0.66
    :✨
    -0.65
    QMetaType
    -0.65
     onAnimation
    -0.65
    Източници
    -0.64
    POSITIVE LOGITS
    WebElementEntity
    0.64
    anghai
    0.47
    bui
    0.45
    oppa
    0.45
     wake
    0.44
     lég
    0.44
    Seeker
    0.44
    нулся
    0.44
    UTIVE
    0.44
    </tfoot>
    0.43
    Act Density 5.008%

    No Known Activations