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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     electrónica
    -0.08
     défis
    -0.08
     Caracas
    -0.08
    hearted
    -0.07
     IFC
    -0.07
     émission
    -0.07
     Faux
    -0.07
     Fiction
    -0.07
     Forbes
    -0.07
    POSITIVE LOGITS
    District
    0.08
     durum
    0.07
    Scenario
    0.07
    Tidak
    0.07
     decides
    0.07
    abla
    0.07
     scenarios
    0.07
    Sorting
    0.07
    0.07
    Lovely
    0.07
    Act Density 0.012%
    No Known Activations