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

    Neuronpedia

    INDEX
    Explanations

    According to the document/text/information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clos
    1.29
    1.20
     με
    1.13
    с
    1.09
    と思います
    1.08
     l
    1.05
     risque
    1.05
    な
    1.00
    のス
    1.00
    וה
    1.00
    POSITIVE LOGITS
    ry
    1.24
    ic
    1.23
    j
    1.22
    au
    1.15
    pyridine
    1.15
    MATRIX
    1.13
    itics
    1.12
    MATH
    1.12
    ren
    1.11
    CR
    1.11
    Act Density 0.048%

    No Known Activations