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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     позд
    -0.08
     will
    -0.07
    波
    -0.07
     tık
    -0.07
    okrat
    -0.06
    appable
    -0.06
     tha
    -0.06
    _LEFT
    -0.06
    ранения
    -0.06
    Distinct
    -0.06
    POSITIVE LOGITS
     recharge
    0.07
     trebuie
    0.06
     tř
    0.06
     Reference
    0.06
     blir
    0.06
     Calif
    0.06
    ================================================================
    0.06
     Kremlin
    0.06
    .gf
    0.06
     alertController
    0.06
    Act Density 0.377%

    No Known Activations