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

    Neuronpedia

    INDEX
    Explanations

    framed photos and wall art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     workloads
    0.39
     overuse
    0.39
     subtypes
    0.39
     concurrency
    0.38
    cidr
    0.38
     simplification
    0.38
     tropos
    0.38
     dependencies
    0.37
    前半
    0.37
     known
    0.37
    POSITIVE LOGITS
     framed
    2.14
    framed
    1.80
     framing
    1.70
     Fram
    1.62
    Fram
    1.61
     frame
    1.60
     frames
    1.57
     Framing
    1.55
     फ्रेम
    1.54
     wall
    1.53
    Act Density 0.013%

    No Known Activations