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

    Neuronpedia

    INDEX
    Explanations

    razy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mlink
    -0.07
     heed
    -0.07
     목록
    -0.07
    öm
    -0.07
    Aff
    -0.07
     берем
    -0.07
     FLAC
    -0.07
     Prof
    -0.07
     lifted
    -0.07
    _eth
    -0.06
    POSITIVE LOGITS
     crazy
    0.18
     Crazy
    0.14
    razy
    0.11
     craz
    0.07
     CRA
    0.07
     cheat
    0.07
    ีความ
    0.07
     cra
    0.07
     random
    0.06
     Candy
    0.06
    Act Density 0.004%

    No Known Activations