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

    Neuronpedia

    INDEX
    Explanations

    sample requests for code, itinerary, resume, soap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     illustrating
    0.49
     drawn
    0.46
     sampler
    0.42
     sculpt
    0.41
     Drawn
    0.40
     tattooing
    0.40
     illustrate
    0.39
     illust
    0.38
     sam
    0.38
     illustrative
    0.38
    POSITIVE LOGITS
     اچھی
    0.45
    अच्छ
    0.45
    bundles
    0.44
    decision
    0.43
    avenir
    0.43
    Hu
    0.42
    KPI
    0.42
     முழு
    0.41
     अच्छी
    0.41
    Fach
    0.40
    Act Density 0.031%

    No Known Activations