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

    Neuronpedia

    INDEX
    Explanations

    how you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mux
    -0.08
    rike
    -0.08
    782
    -0.08
     backdrop
    -0.08
    oug
    -0.08
     यह
    -0.08
    ạng
    -0.08
    ninger
    -0.08
     jugg
    -0.08
    å¥Ĺ
    -0.08
    POSITIVE LOGITS
     you
    0.13
    omorphic
    0.12
     could
    0.10
     puedes
    0.10
    å¦Ĥä½ķ
    0.09
     thá»ĥ
    0.09
     Gust
    0.09
    ··
    0.09
    dy
    0.08
     Elias
    0.08
    Act Density 0.085%

    No Known Activations