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
     fosse
    -0.07
     chyba
    -0.07
     compilation
    -0.07
     tivesse
    -0.07
     subplot
    -0.07
    积分
    -0.07
     beck
    -0.07
     scuba
    -0.07
    ficiency
    -0.07
     voluptate
    -0.07
    POSITIVE LOGITS
     crossings
    0.09
     تون
    0.08
     সাক্ষ
    0.08
     Celt
    0.08
     روند
    0.08
     exiting
    0.08
     ontwikkelingen
    0.08
    кор
    0.08
    কৰ
    0.08
     sightings
    0.08
    Act Density 0.010%

    No Known Activations