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

    Neuronpedia

    INDEX
    Explanations

    spring, term limits, sushi, expected time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spring
    0.44
     sprink
    0.43
    spring
    0.39
    ின்ன
    0.38
    sine
    0.38
    termin
    0.37
     fuente
    0.36
     acceso
    0.36
     اصلی
    0.36
    sina
    0.36
    POSITIVE LOGITS
     patern
    0.44
     Projects
    0.43
     bereaved
    0.43
     Magnificent
    0.42
     mammalian
    0.40
     marvelous
    0.40
     branchNode
    0.40
    ▋
    0.40
     bombings
    0.40
    摑
    0.40
    Act Density 0.001%

    No Known Activations