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

    Neuronpedia

    INDEX
    Explanations

    giving a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    q
    0.66
     seniors
    0.62
    torque
    0.62
     Nor
    0.62
     weaker
    0.61
     Nad
    0.61
    assoc
    0.61
    primer
    0.61
     q
    0.60
     Fatigue
    0.60
    POSITIVE LOGITS
     spectacular
    0.92
     искус
    0.92
     wildly
    0.90
     dazzling
    0.89
     widely
    0.87
     ярко
    0.86
     artificially
    0.84
     অবশ্যই
    0.84
     speedily
    0.84
    ¡
    0.84
    Act Density 0.013%

    No Known Activations