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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chi
    -0.08
    QUIRES
    -0.07
    rell
    -0.07
     warrant
    -0.07
    (payload
    -0.06
    منت
    -0.06
     photon
    -0.06
    论文
    -0.06
    surname
    -0.06
     Mn
    -0.06
    POSITIVE LOGITS
    常常
    0.07
     médec
    0.07
    様々
    0.07
    ㈪
    0.07
     DataContext
    0.07
     {↵↵
    0.06
    /unit
    0.06
    钚
    0.06
     Desk
    0.06
    /payment
    0.06
    Act Density 0.002%

    No Known Activations