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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _schema
    -0.07
    _two
    -0.07
     centralized
    -0.06
    /tos
    -0.06
     FITNESS
    -0.06
    داری
    -0.06
    Heat
    -0.06
    ỳ
    -0.06
     meaningful
    -0.06
     aumento
    -0.06
    POSITIVE LOGITS
     Celebr
    0.07
    まと
    0.06
     получить
    0.06
     Techniques
    0.06
    uyordu
    0.06
    iết
    0.06
    ünst
    0.06
     quan
    0.06
    िष
    0.06
    shint
    0.06
    Act Density 0.030%

    No Known Activations