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

    Neuronpedia

    INDEX
    Explanations

    code snippets and structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erfolgen
    0.48
    ล
    0.48
     Chapters
    0.47
    כ
    0.47
    晞
    0.47
    >'
    0.46
    щается
    0.46
    带来
    0.46
    у
    0.46
     chapters
    0.45
    POSITIVE LOGITS
    spanning
    0.47
    shipping
    0.44
    specification
    0.44
     FSB
    0.44
    optimal
    0.43
    still
    0.43
    PRET
    0.42
    FG
    0.42
     EGR
    0.42
    !),
    0.42
    Act Density 0.000%

    No Known Activations