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

    Neuronpedia

    INDEX
    Explanations

    audio or sensor data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     know
    0.97
     KNOW
    0.77
     Know
    0.74
    know
    0.74
    Know
    0.74
     Year
    0.74
     year
    0.74
     incentivize
    0.72
     knows
    0.71
     biết
    0.69
    POSITIVE LOGITS
    CLUDED
    0.82
    panion
    0.77
    TypeList
    0.75
    ികളും
    0.74
     الم
    0.73
     elytris
    0.72
    onnage
    0.71
    بة
    0.71
    দাতা
    0.70
    illation
    0.70
    Act Density 0.000%

    No Known Activations