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

    Neuronpedia

    INDEX
    Explanations

    RN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Initializer
    -0.07
     sub
    -0.07
    ندر
    -0.06
    Hur
    -0.06
    Pos
    -0.06
     craftsmanship
    -0.06
     bottleneck
    -0.06
     Maur
    -0.06
     theta
    -0.06
     문서
    -0.06
    POSITIVE LOGITS
    탁
    0.07
    により
    0.07
    τρ
    0.06
    rn
    0.06
     hodiny
    0.06
    RN
    0.06
    /logout
    0.06
     Parsons
    0.06
    (^
    0.06
    (samples
    0.06
    Act Density 0.002%

    No Known Activations