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

    Neuronpedia

    INDEX
    Explanations

    familiarity and commonality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.98
    ?
    0.94
     hidrat
    0.77
     financi
    0.75
    لي
    0.73
    an
    0.72
    ed
    0.72
    </u>
    0.71
    </h2>
    0.70
     amit
    0.70
    POSITIVE LOGITS
    familiar
    0.95
    다
    0.93
     familiarity
    0.93
    system
    0.92
    ר
    0.86
    রার
    0.86
     unfamiliar
    0.85
     accustomed
    0.84
    amiliar
    0.84
    ა
    0.83
    Act Density 0.018%

    No Known Activations