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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valiant
    1.28
     twisted
    1.28
     luxurious
    1.19
     lus
    1.18
     crumpled
    1.16
     vigilant
    1.15
    elsch
    1.15
    <unused301>
    1.11
     restless
    1.11
    期間限定
    1.11
    POSITIVE LOGITS
    k
    1.45
    t
    1.32
    l
    1.30
    d
    1.28
    b
    1.25
    tries
    1.23
    p
    1.18
    rements
    1.16
    y
    1.15
    n
    1.14
    Act Density 0.000%

    No Known Activations