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

    Neuronpedia

    INDEX
    Explanations

    drawing shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    篇
    -0.07
     Crypt
    -0.06
     Stanley
    -0.06
     ERP
    -0.06
    (uri
    -0.06
    _dt
    -0.06
     PAY
    -0.06
    ここ
    -0.06
    達
    -0.06
     bouquet
    -0.06
    POSITIVE LOGITS
    .console
    0.07
    .LabelControl
    0.06
    plements
    0.06
     Başkanı
    0.06
    anyl
    0.06
     argued
    0.06
    СТ
    0.06
     Trials
    0.06
     traitement
    0.06
     disadv
    0.06
    Act Density 0.011%

    No Known Activations