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

    Neuronpedia

    INDEX
    Explanations

    suggest identification executable ROM kernel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nightmares
    0.45
    ྀ
    0.44
     disastrous
    0.44
     sesize
    0.43
     injustices
    0.42
     tyrannical
    0.42
     threatens
    0.41
     dete
    0.41
     cassettes
    0.41
     capsules
    0.41
    POSITIVE LOGITS
    uyo
    0.44
    ograf
    0.42
    Writer
    0.41
    getWidth
    0.40
    DownLatch
    0.40
    uchtigkeit
    0.39
    odot
    0.39
     бібліоте
    0.39
    irk
    0.38
    äck
    0.38
    Act Density 0.001%

    No Known Activations