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

    Neuronpedia

    INDEX
    Explanations

    news agency, dates, dispatch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DAY
    0.69
    ру
    0.68
    DOC
    0.67
    SAP
    0.64
    DATE
    0.62
    emph
    0.61
    liness
    0.60
    рки
    0.60
    Type
    0.58
     charm
    0.58
    POSITIVE LOGITS
    hatikan
    0.72
     Buhari
    0.71
    ب
    0.71
    °;
    0.70
    ющимся
    0.68
     معاون
    0.68
    ிரஸ்
    0.68
     ![](
    0.68
    য়োজন
    0.68
     masculinity
    0.67
    Act Density 0.004%

    No Known Activations