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

    Neuronpedia

    INDEX
    Explanations

    drawing, managers, concurrency, powder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XL
    0.40
     específicamente
    0.40
    Purple
    0.39
    ulta
    0.38
    धी
    0.37
     specifically
    0.37
    acy
    0.36
    hud
    0.36
    బో
    0.36
     purchaser
    0.36
    POSITIVE LOGITS
     geschaffen
    0.40
     लगे
    0.39
    氵
    0.39
     allev
    0.39
     প্রতিক
    0.38
     Mbps
    0.38
     solusi
    0.38
     gota
    0.37
     >,
    0.37
     സോ
    0.36
    Act Density 0.000%

    No Known Activations