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

    Neuronpedia

    INDEX
    Explanations

    sonic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中央
    -0.08
    τρέ
    -0.08
    л
    -0.08
     donnée
    -0.07
     데이터를
    -0.07
    ندی
    -0.07
     centrally
    -0.07
    Activities
    -0.07
    ுகிறது
    -0.07
    тел
    -0.07
    POSITIVE LOGITS
    vette
    0.08
     douche
    0.08
     screwdriver
    0.08
     дым
    0.08
     Nell
    0.08
     declarations
    0.07
     उद्घ
    0.07
     Caller
    0.07
     eche
    0.07
     iche
    0.07
    Act Density 0.004%

    No Known Activations