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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     which
    -0.07
     repeated
    -0.07
     whom
    -0.07
     Motors
    -0.07
     Martin
    -0.07
    _numeric
    -0.06
     και
    -0.06
    天
    -0.06
     remark
    -0.06
     Elliot
    -0.06
    POSITIVE LOGITS
    �
    0.06
    nah
    0.06
     пром
    0.06
    엔
    0.06
    폴
    0.06
     압
    0.06
     soaking
    0.06
    alary
    0.06
    ousy
    0.06
    िफ
    0.06
    Act Density 0.026%

    No Known Activations