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
    .Utils
    -0.07
    iates
    -0.07
    　　　
    -0.07
     Knoxville
    -0.06
    eras
    -0.06
    [h
    -0.06
     dataList
    -0.06
    YOU
    -0.06
    IllegalArgumentException
    -0.06
     nosotros
    -0.06
    POSITIVE LOGITS
    ันออก
    0.07
     enabling
    0.06
    /inet
    0.06
     말이
    0.06
     เล
    0.06
     Ez
    0.06
     quadr
    0.06
     hyp
    0.06
    approval
    0.06
     weighing
    0.06
    Act Density 0.005%

    No Known Activations