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

    Neuronpedia

    INDEX
    Explanations

    specialized terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.39
    us
    0.37
    (
    0.35
    it
    0.34
    ring
    0.34
    ids
    0.34
    )
    0.34
    is
    0.33
    uri
    0.33
    res
    0.33
    POSITIVE LOGITS
     étude
    0.33
     allemand
    0.32
    тие
    0.31
     jährlich
    0.31
     uczni
    0.30
    ر
    0.30
    كان
    0.30
    ঙ্ক
    0.30
     yeni
    0.30
     ofertas
    0.30
    Act Density 0.695%

    No Known Activations