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

    Neuronpedia

    INDEX
    Explanations

    your name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    दरअसल
    0.62
     their
    0.62
    eo
    0.61
    логии
    0.61
     itself
    0.61
    **
    0.60
     deres
    0.59
    SimpleDateFormat
    0.56
     उन्‍हें
    0.56
     jejich
    0.56
    POSITIVE LOGITS
     Own
    1.30
     own
    1.27
     Highness
    1.16
     thoughts
    1.15
     favorite
    1.10
     Lieblings
    1.07
    Own
    1.04
     Favorite
    1.02
     favourite
    1.01
     attitude
    1.01
    Act Density 0.094%

    No Known Activations