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

    Neuronpedia

    INDEX
    Explanations

    presentation slides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prüfung
    0.34
     suss
    0.34
    沉
    0.33
    eek
    0.33
    ieve
    0.33
     أهل
    0.33
    ⎪
    0.32
    across
    0.32
     adversaries
    0.32
    boolProp
    0.32
    POSITIVE LOGITS
     slide
    0.60
     slides
    0.54
     Slide
    0.54
     слай
    0.52
     Slides
    0.51
    Slide
    0.48
    Slides
    0.47
     स्लाइड
    0.45
    slides
    0.44
    slide
    0.42
    Act Density 0.000%

    No Known Activations