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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Resource
    -0.07
     limiting
    -0.07
     ama
    -0.06
    977
    -0.06
     Chop
    -0.06
    ccc
    -0.06
     colonization
    -0.06
     incoming
    -0.06
    Scaling
    -0.06
    обыти
    -0.06
    POSITIVE LOGITS
     食
    0.06
    LOPT
    0.06
     veloc
    0.06
     backlight
    0.06
     broadcaster
    0.06
     bất
    0.06
    ولة
    0.06
    _PORTS
    0.06
    _[
    0.06
    rowave
    0.06
    Act Density 0.015%

    No Known Activations