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

    Neuronpedia

    INDEX
    Explanations

    generating model output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    namese
    0.40
    actone
    0.39
    insights
    0.39
    Entrepreneur
    0.39
    Directors
    0.39
    think
    0.38
    egang
    0.38
     Entrepreneurs
    0.37
    Think
    0.37
    创始人
    0.36
    POSITIVE LOGITS
     okay
    0.42
     Okay
    0.41
     Made
    0.41
     disclaimer
    0.39
    Okay
    0.39
    Made
    0.39
    ழும்
    0.38
     preamble
    0.38
     Sorry
    0.38
     Poem
    0.38
    Act Density 0.092%

    No Known Activations