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

    Neuronpedia

    INDEX
    Explanations

    interested in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    젊
    0.78
    itochond
    0.77
     ಸ್ನೇಹಿತ
    0.77
    وت
    0.77
     moyens
    0.76
     semplici
    0.75
    𠄌
    0.75
    ՜
    0.74
     verme
    0.74
     트리
    0.74
    POSITIVE LOGITS
     Of
    0.97
     Upon
    0.88
    Of
    0.84
     With
    0.82
     Should
    0.79
     upon
    0.79
     Which
    0.76
     And
    0.76
    With
    0.73
     Against
    0.72
    Act Density 0.156%

    No Known Activations