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

    Neuronpedia

    INDEX
    Explanations

    list of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zelfde
    0.98
    iru
    0.89
    ры
    0.88
    ל
    0.87
    ül
    0.86
    ﺤ
    0.84
    мы
    0.83
    んですよ
    0.83
    ০
    0.83
    んですよね
    0.82
    POSITIVE LOGITS
     commend
    1.09
     beacons
    1.00
     goodies
    0.98
     labs
    0.98
     regrett
    0.95
     suppos
    0.94
     lapses
    0.93
     consultations
    0.89
     faç
    0.89
     lenders
    0.89
    Act Density 0.000%

    No Known Activations