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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liebe
    -0.07
    Top
    -0.07
     kdyby
    -0.06
     hỏi
    -0.06
    ullah
    -0.06
    .stamp
    -0.06
     вне
    -0.06
    "));
    -0.06
     파일첨부
    -0.06
     Kle
    -0.06
    POSITIVE LOGITS
     vzdu
    0.07
    003
    0.07
     أث
    0.07
    ARI
    0.07
    02
    0.07
    004
    0.07
     司
    0.07
    arius
    0.07
     Rail
    0.07
    804
    0.07
    Act Density 0.017%

    No Known Activations