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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Budget
    -0.07
     Kıs
    -0.07
     foods
    -0.06
     �
    -0.06
    adian
    -0.06
    $/)
    -0.06
     Berk
    -0.06
    _reward
    -0.06
     пенс
    -0.06
    Markers
    -0.06
    POSITIVE LOGITS
    مام
    0.07
     ­
    0.06
     junge
    0.06
    ren
    0.06
     philosoph
    0.06
     LastName
    0.06
    엔
    0.06
     unfamiliar
    0.06
    vir
    0.06
     Website
    0.06
    Act Density 0.050%

    No Known Activations