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

    Neuronpedia

    INDEX
    Explanations

    executive summary and document versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    怎样
    0.42
    ßerdem
    0.41
    使
    0.41
     nonuniform
    0.40
     그다음에
    0.39
     uitle
    0.39
     explanation
    0.39
     misure
    0.39
    >∕
    0.39
     explanations
    0.38
    POSITIVE LOGITS
    pdf
    0.68
    Prepared
    0.64
    Executive
    0.60
    Compiled
    0.58
     Prepared
    0.57
    PDF
    0.56
     Presented
    0.55
     Compiled
    0.55
    Presented
    0.54
    Version
    0.54
    Act Density 0.110%

    No Known Activations