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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     federation
    -0.07
    효
    -0.07
     lun
    -0.06
    ९
    -0.06
     гот
    -0.06
    \Collection
    -0.06
    沈
    -0.06
    rove
    -0.06
     tập
    -0.06
     Zem
    -0.06
    POSITIVE LOGITS
    inkel
    0.08
    programs
    0.07
     giành
    0.07
     angle
    0.07
     ↵
    0.07
    coder
    0.07
     sparked
    0.07
     objev
    0.06
     Quando
    0.06
     clap
    0.06
    Act Density 0.006%

    No Known Activations