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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cosmic
    -0.07
    hum
    -0.06
    週
    -0.06
     tensorflow
    -0.06
     inverse
    -0.06
     Tok
    -0.06
    uyo
    -0.06
     computers
    -0.06
     regulator
    -0.06
     parametro
    -0.06
    POSITIVE LOGITS
     DELETE
    0.07
    _memory
    0.07
    /current
    0.07
     낮
    0.06
    جيل
    0.06
    _OPTIONS
    0.06
     Programmer
    0.06
    ='../
    0.06
    (ct
    0.06
     jel
    0.06
    Act Density 0.041%

    No Known Activations