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

    Neuronpedia

    INDEX
    Explanations

    as a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هههه
    1.17
     Maugin
    1.13
    een
    1.12
    r
    1.10
     conti
    1.03
     fatta
    1.02
    o
    1.02
     fratt
    0.99
     społ
    0.96
     boyhood
    0.96
    POSITIVE LOGITS
    й
    1.34
    ids
    1.32
     значений
    1.16
    schluss
    1.14
    ime
    1.11
    за
    1.10
    ку
    1.10
    нік
    1.10
    یا
    1.09
    newlines
    1.09
    Act Density 0.055%

    No Known Activations