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

    Neuronpedia

    INDEX
    Explanations

    creating something new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dumb
    -0.07
     SQLAlchemy
    -0.07
     Rehab
    -0.06
    ulario
    -0.06
     Early
    -0.06
     Aralık
    -0.06
     telegram
    -0.06
    Beer
    -0.06
    ตำ
    -0.06
    адки
    -0.06
    POSITIVE LOGITS
     Wass
    0.06
    Msg
    0.06
    шир
    0.06
    اسر
    0.06
    learner
    0.06
     mk
    0.06
     create
    0.06
    _deinit
    0.06
    _results
    0.06
    (cs
    0.06
    Act Density 0.104%

    No Known Activations