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

    Neuronpedia

    INDEX
    Explanations

    coding/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JM
    -0.07
    碰
    -0.07
     fak
    -0.07
     Facility
    -0.06
    :bold
    -0.06
     Wong
    -0.06
     Slate
    -0.06
     seminars
    -0.06
     jelly
    -0.06
    KM
    -0.06
    POSITIVE LOGITS
    악
    0.07
    ừa
    0.06
    ρηση
    0.06
    chluss
    0.06
    ("."
    0.06
    "",
    0.06
    "",↵
    0.06
    _ERR
    0.06
     المش
    0.06
    (default
    0.06
    Act Density 0.006%

    No Known Activations