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

    Neuronpedia

    INDEX
    Explanations

    specifically in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATIVE
    0.87
    ự
    0.85
    스를
    0.81
    峒
    0.81
     страницы
    0.77
    Tracy
    0.75
    COVER
    0.75
    𝐣
    0.75
     atha
    0.75
    Ordine
    0.75
    POSITIVE LOGITS
    ان
    0.97
    ⟋
    0.86
    我
    0.80
     Networking
    0.77
     Filtering
    0.77
    我又
    0.77
     NPTypeCode
    0.76
    我对
    0.76
     Calculation
    0.75
     reworked
    0.75
    Act Density 0.000%

    No Known Activations