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

    Neuronpedia

    INDEX
    Explanations

    If followed by controller

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     G
    0.44
     Gon
    0.41
     Mito
    0.40
     Gy
    0.40
     Gallagher
    0.39
    lays
    0.39
     Gle
    0.38
    otica
    0.38
     Hasta
    0.38
     Grig
    0.38
    POSITIVE LOGITS
    bdd
    0.48
    yc
    0.44
     promulg
    0.41
     अंतिम
    0.40
     ४
    0.40
     су
    0.39
     اربع
    0.39
     suara
    0.39
     تحدث
    0.39
     zákon
    0.38
    Act Density 0.000%

    No Known Activations