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

    Neuronpedia

    INDEX
    Explanations

    desperate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obao
    -0.07
    وك
    -0.07
    _probe
    -0.07
    ้ม
    -0.07
     ward
    -0.07
    .then
    -0.07
    ම
    -0.07
    =search
    -0.06
    (infile
    -0.06
    basic
    -0.06
    POSITIVE LOGITS
    фи
    0.08
     ска
    0.07
    '})↵↵
    0.07
     bindActionCreators
    0.07
     desper
    0.07
    ounters
    0.07
     Helena
    0.07
     desperate
    0.07
     Carnegie
    0.07
    düğü
    0.07
    Act Density 0.005%

    No Known Activations