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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，并
    -0.07
     occupancy
    -0.07
     puntos
    -0.06
    anse
    -0.06
    rar
    -0.06
     Jim
    -0.06
     čty
    -0.06
     título
    -0.06
    Дж
    -0.06
    _SECRET
    -0.06
    POSITIVE LOGITS
     //}↵
    0.07
    _global
    0.07
    ูกค
    0.06
    <?>>
    0.06
     eliminated
    0.06
    _timezone
    0.06
     ------>
    0.06
    inv
    0.06
    _nat
    0.06
     qreal
    0.06
    Act Density 0.002%

    No Known Activations