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

    Neuronpedia

    INDEX
    Explanations

    slide titles and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seamen
    0.52
     betas
    0.50
     commissary
    0.50
    sadpoetry
    0.49
    PlayerDataCache
    0.48
     ateliers
    0.48
     bureaucratic
    0.47
     nematode
    0.47
     dinners
    0.47
     methylation
    0.46
    POSITIVE LOGITS
     Slide
    0.90
     slide
    0.89
     Slides
    0.88
     PowerPoint
    0.85
    Slide
    0.80
     slides
    0.80
     слай
    0.73
    slide
    0.71
    slides
    0.63
    Slides
    0.63
    Act Density 0.032%

    No Known Activations