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

    Neuronpedia

    INDEX
    Explanations

    conceptual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     QRect
    -0.07
     weaknesses
    -0.07
     AREA
    -0.07
     Lond
    -0.07
     Japon
    -0.06
    ód
    -0.06
     тов
    -0.06
    hed
    -0.06
     повіт
    -0.06
     ناحیه
    -0.06
    POSITIVE LOGITS
     conceptual
    0.08
    .SelectCommand
    0.07
     anticip
    0.06
     sparing
    0.06
    サイ
    0.06
    験
    0.06
    SPA
    0.06
     resemble
    0.06
    AINER
    0.06
    менно
    0.06
    Act Density 0.023%

    No Known Activations