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

    Neuronpedia

    INDEX
    Explanations

    informal writing/blogs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Airport
    -0.07
     bartender
    -0.07
    _review
    -0.07
    'ya
    -0.07
    _OPERATION
    -0.06
     amps
    -0.06
     patient
    -0.06
    friendly
    -0.06
     FIR
    -0.06
    lng
    -0.06
    POSITIVE LOGITS
    /div
    0.06
    -graph
    0.06
    ulpt
    0.06
    _big
    0.06
     aVar
    0.06
    ไทย
    0.06
    [list
    0.06
    .tap
    0.06
    _post
    0.06
     dönüş
    0.06
    Act Density 0.033%

    No Known Activations