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

    Neuronpedia

    INDEX
    Explanations

    emotions/feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curse
    -0.08
     Maths
    -0.08
    urllib
    -0.07
    URLConnection
    -0.07
     Dauer
    -0.07
    يدي
    -0.07
     sitcom
    -0.07
     WIN
    -0.07
    ىرى
    -0.07
     urllib
    -0.07
    POSITIVE LOGITS
    abilities
    0.08
     목록
    0.08
    abulary
    0.08
    ართლ
    0.08
    аран
    0.07
    ếc
    0.07
    ute
    0.07
    ogram
    0.07
     roster
    0.07
     genomes
    0.07
    Act Density 0.001%

    No Known Activations