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

    Neuronpedia

    INDEX
    Explanations

    but possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inig
    0.48
    smiling
    0.47
    ėje
    0.47
    ɩ
    0.47
    ję
    0.45
     предложение
    0.45
    Proposed
    0.45
     ጨ
    0.44
    𝐝
    0.44
    Delete
    0.44
    POSITIVE LOGITS
     đây
    0.49
     emphasizes
    0.49
    द्दल
    0.45
     aggiunto
    0.44
     اہم
    0.43
     Impact
    0.42
     Cine
    0.41
     important
    0.41
     trí
    0.41
     wichtigsten
    0.41
    Act Density 0.006%

    No Known Activations