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

    Neuronpedia

    INDEX
    Explanations

    () and ();

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1744>
    0.76
    <unused893>
    0.72
    <unused2222>
    0.70
    <unused948>
    0.67
    <unused2140>
    0.65
    <unused300>
    0.64
    <unused279>
    0.62
    ધું
    0.62
    <unused649>
    0.62
     Moscow
    0.61
    POSITIVE LOGITS
    ／
    0.69
    :///
    0.65
     ()
    0.63
     ();
    0.61
    ();
    0.61
    ّ
    0.61
     ($
    0.61
     ().
    0.60
    ـــ
    0.59
    ():
    0.58
    Act Density 0.179%

    No Known Activations