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

    Neuronpedia

    INDEX
    Explanations

    Likert scale items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Α
    1.01
    ور
    0.98
    ，
    0.88
    T
    0.87
    一
    0.85
    ई
    0.83
    <0x0D>
    0.80
    Ф
    0.80
    افة
    0.79
    कर
    0.79
    POSITIVE LOGITS
    in
    1.59
    to
    1.18
     to
    0.99
     not
    0.91
    inę
    0.91
    лна
    0.90
    ാ
    0.89
    inį
    0.88
     তবে
    0.87
    ే
    0.85
    Act Density 0.000%

    No Known Activations