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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Qualifier
    -0.07
    _letters
    -0.07
     IDictionary
    -0.07
    Illustr
    -0.06
     novelty
    -0.06
    ολ
    -0.06
     сл
    -0.06
    ớp
    -0.06
    骑
    -0.06
     utiliser
    -0.06
    POSITIVE LOGITS
    alls
    0.07
    сии
    0.06
    Http
    0.06
    ій
    0.06
     Homework
    0.06
    اعة
    0.06
     процессе
    0.06
    ews
    0.06
    ektedir
    0.06
    _PHY
    0.06
    Act Density 0.001%

    No Known Activations