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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depos
    -0.07
     pé
    -0.07
     Parliamentary
    -0.06
     Singh
    -0.06
     hot
    -0.06
    [op
    -0.06
    (parsed
    -0.06
     pseudo
    -0.06
     IOException
    -0.06
     tents
    -0.06
    POSITIVE LOGITS
    jylland
    0.06
    mare
    0.06
     aktuellen
    0.06
     ullam
    0.06
    .View
    0.06
    νονται
    0.06
    reck
    0.06
    фіка
    0.06
     minorities
    0.06
     thirds
    0.06
    Act Density 0.002%

    No Known Activations