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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    董
    -0.07
    urtles
    -0.07
     watershed
    -0.07
    battery
    -0.07
     بدن
    -0.06
    Pri
    -0.06
     通
    -0.06
     کودکان
    -0.06
     Sem
    -0.06
    通
    -0.06
    POSITIVE LOGITS
    .finish
    0.07
     fa
    0.07
     labore
    0.06
    ото
    0.06
     ok
    0.06
    016
    0.06
    оля
    0.06
    STONE
    0.06
     os
    0.06
    England
    0.06
    Act Density 0.009%

    No Known Activations