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

    Neuronpedia

    INDEX
    Explanations

    Content-Type header

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uvi
    1.00
    ]=(
    0.92
    इट
    0.92
     prized
    0.89
    <0xB1>
    0.85
     incul
    0.85
     ${_
    0.84
     unsuccessfully
    0.82
     impatiently
    0.81
    golden
    0.80
    POSITIVE LOGITS
    จ
    0.81
    PushButton
    0.78
     Burr
    0.78
     Justicia
    0.74
     biss
    0.73
    ೋಗ್ಯ
    0.72
     Amph
    0.72
     wohl
    0.72
    foaf
    0.71
     ma
    0.71
    Act Density 0.001%

    No Known Activations