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

    Neuronpedia

    INDEX
    Explanations

    process template

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.62
    ot
    0.59
    on
    0.55
    rath
    0.55
    od
    0.53
    ent
    0.52
    ed
    0.52
    elon
    0.48
     {$
    0.48
    onov
    0.47
    POSITIVE LOGITS
    İ
    0.61
    アリ
    0.50
     үш
    0.50
     Ainda
    0.49
     июле
    0.48
     задержа
    0.47
    íram
    0.47
    」
    0.47
     După
    0.47
    </h2>
    0.47
    Act Density 0.000%

    No Known Activations