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

    Neuronpedia

    INDEX
    Explanations

    Figure/citation references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Substitute
    -0.08
     Lynn
    -0.07
     Flags
    -0.06
     Grand
    -0.06
     Paid
    -0.06
    Bitmap
    -0.06
     Ont
    -0.06
     تلویزیون
    -0.06
    版本
    -0.06
     fichier
    -0.06
    POSITIVE LOGITS
    пп
    0.06
     additives
    0.06
    <translation
    0.06
     relevance
    0.06
     císa
    0.06
     butto
    0.06
     السي
    0.06
    /embed
    0.06
    енню
    0.06
    .lot
    0.06
    Act Density 0.002%

    No Known Activations