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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]):
↵
    -0.07
    SES
    -0.06
    annel
    -0.06
    _CC
    -0.06
    .getOrElse
    -0.06
     IMPORTANT
    -0.06
     Bulk
    -0.06
     발
    -0.06
    >{↵
    -0.06
    //----------------------------------------------------------------------------------------------------------------
    -0.06
    POSITIVE LOGITS
    181
    0.07
     hotels
    0.07
     jeopardy
    0.07
     Đối
    0.06
    IQ
    0.06
    녀
    0.06
    ะแนน
    0.06
     siege
    0.06
     alıyor
    0.06
    เมตร
    0.06
    Act Density 0.006%

    No Known Activations