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

    Neuronpedia

    INDEX
    Explanations

    honest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     connecting
    -0.47
    باب
    -0.47
     living
    -0.47
    ']):
    -0.47
    <bos>
    -0.47
     with
    -0.46
     cu
    -0.46
     preferring
    -0.46
     d
    -0.46
     pul
    -0.45
    POSITIVE LOGITS
    migrationBuilder
    0.91
    ^(@)
    0.69
     المعيارى
    0.69
    Джерело
    0.68
     kaarangay
    0.67
     للمعارف
    0.66
     fevere
    0.64
     habet
    0.64
    Personendaten
    0.64
     realises
    0.64
    Act Density 0.147%

    No Known Activations