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

    Neuronpedia

    INDEX
    Explanations

    spectral ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     release
    -0.07
    -team
    -0.07
     Governance
    -0.07
    니
    -0.07
    -0.06
     راه
    -0.06
     Cavaliers
    -0.06
     republic
    -0.06
     aircraft
    -0.06
    běh
    -0.06
    POSITIVE LOGITS
     preseason
    0.06
     flock
    0.06
    ają
    0.06
     проек
    0.06
     Schwartz
    0.06
    \"><
    0.06
     XCTestCase
    0.06
    itom
    0.06
     *↵↵
    0.06
     Pascal
    0.06
    Act Density 0.034%

    No Known Activations