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

    Neuronpedia

    INDEX
    Explanations

    recipe timings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sunline
    0.43
     კომ
    0.35
    hém
    0.34
     cosm
    0.34
     ಹೇ
    0.34
    ikom
    0.33
    แค
    0.32
    orado
    0.32
     سونے
    0.32
    群
    0.32
    POSITIVE LOGITS
     وو
    0.38
     confiar
    0.38
     ২৬
    0.36
     Econom
    0.36
     प्रतिदिन
    0.35
    بيوتر
    0.35
     कुल
    0.35
     Fancy
    0.34
     ля
    0.34
     practicar
    0.34
    Act Density 0.003%

    No Known Activations