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

    Neuronpedia

    INDEX
    Explanations

    diff markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.52
    S
    1.50
    E
    1.49
    ه
    1.43
    e
    1.34
    ে
    1.33
    H
    1.22
    ு
    1.21
    U
    1.20
    N
    1.20
    POSITIVE LOGITS
     interstitiis
    1.42
    ၜ
    1.38
    ួត
    1.37
    <unused2058>
    1.35
    Traversal
    1.32
     وبركاته
    1.31
     efektif
    1.31
     aard
    1.30
     deformations
    1.27
    gå
    1.27
    Act Density 0.000%

    No Known Activations