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

    Neuronpedia

    INDEX
    Explanations

    shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     synerg
    -0.08
     supplemental
    -0.08
     المتعلقة
    -0.08
     electrolyte
    -0.08
     חש
    -0.08
     החש
    -0.08
     infrastructure
    -0.07
     والش
    -0.07
     verantwort
    -0.07
     إدارة
    -0.07
    POSITIVE LOGITS
    quarter
    0.10
    -shaped
    0.09
     doble
    0.08
    堵
    0.08
    bags
    0.08
    -fitting
    0.08
    past
    0.08
    wise
    0.08
     pea
    0.08
     quarter
    0.08
    Act Density 0.017%

    No Known Activations