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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     observ
    -0.09
     observable
    -0.08
    $b
    -0.08
    เอ
    -0.08
     refers
    -0.07
    Si
    -0.07
     vans
    -0.07
     Observable
    -0.07
    -0.07
    .observable
    -0.07
    POSITIVE LOGITS
     года
    0.10
     ವರ್ಷದ
    0.10
     night's
    0.10
     року
    0.09
    oday
    0.09
     రోజు
    0.09
     luck
    0.09
     gün
    0.09
     dní
    0.09
     yıl
    0.09
    Act Density 0.042%
    No Known Activations