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

    Neuronpedia

    INDEX
    Explanations

    Bezier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    成绩
    -0.07
     prima
    -0.07
     impactful
    -0.07
     intelligence
    -0.06
     limitless
    -0.06
     myst
    -0.06
    (It
    -0.06
    .mask
    -0.06
    OM
    -0.06
     Моск
    -0.06
    POSITIVE LOGITS
    .Permission
    0.06
    accountId
    0.06
    centers
    0.06
     sqr
    0.06
     позвол
    0.06
     Lewis
    0.06
    linked
    0.06
    (rr
    0.06
    .Payload
    0.06
    .choices
    0.06
    Act Density 0.007%

    No Known Activations