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

    Neuronpedia

    INDEX
    Explanations

    espnricinfo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.86
    locationY
    1.80
    ות
    1.77
    Maritime
    1.73
    ﺔ
    1.73
    Whatever
    1.71
    tener
    1.67
    לק
    1.67
    싶
    1.66
     coisas
    1.66
    POSITIVE LOGITS
     hydraulic
    1.87
     disband
    1.75
     utilizzati
    1.69
     platoon
    1.67
     lows
    1.67
     dissolving
    1.66
     dodging
    1.64
     financing
    1.63
     Margaret
    1.62
    நடிக
    1.61
    Act Density 0.000%

    No Known Activations