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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pral
    -0.08
    030
    -0.07
    yek
    -0.07
    өлөр
    -0.07
    -lhe
    -0.07
     slam
    -0.07
    ತ್ತು
    -0.07
    弹
    -0.07
    ತ್ಸ
    -0.07
     cek
    -0.07
    POSITIVE LOGITS
     روح
    0.08
     benchmarks
    0.08
    月份
    0.08
     لما
    0.07
    .Publish
    0.07
    .ceil
    0.07
     संस्थ
    0.07
     لمع
    0.07
     मार्क
    0.07
     👍
    0.07
    Act Density 0.000%

    No Known Activations