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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Addition
    -0.07
    ervals
    -0.06
    _root
    -0.06
     afin
    -0.06
     省
    -0.06
    ål
    -0.06
     Any
    -0.06
     př
    -0.06
     Decoder
    -0.06
    veyor
    -0.06
    POSITIVE LOGITS
     Sean
    0.07
    الأ
    0.07
    _gene
    0.07
    ;',↵
    0.06
     силы
    0.06
    -issue
    0.06
    ToDate
    0.06
     tart
    0.06
     aspir
    0.06
    載
    0.06
    Act Density 0.002%

    No Known Activations