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

    Neuronpedia

    INDEX
    Explanations

    math operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &,
    -0.07
     behaving
    -0.07
     завтра
    -0.07
    formats
    -0.06
    .proxy
    -0.06
    !='
    -0.06
     slides
    -0.06
     zipcode
    -0.06
     Pen
    -0.06
    _Offset
    -0.06
    POSITIVE LOGITS
    asar
    0.07
    ’я
    0.07
    uely
    0.07
    .YesNo
    0.06
    　　 　 　 　
    0.06
    AGER
    0.06
    oy
    0.06
    esan
    0.06
    @nate
    0.06
    //**↵
    0.06
    Act Density 0.006%

    No Known Activations