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

    Neuronpedia

    INDEX
    Explanations

    app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.94
    ی
    0.86
    ς
    0.86
     have
    0.75
    have
    0.71
     HAVE
    0.70
    வின்
    0.68
    s
    0.68
    יא
    0.68
    ޟ
    0.66
    POSITIVE LOGITS
    ra
    0.85
    ong
    0.68
    la
    0.66
     ότι
    0.64
     glimpses
    0.63
    endente
    0.62
     שה
    0.62
    "],
    0.61
     అంద
    0.61
    0
    0.61
    Act Density 0.016%

    No Known Activations