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

    Neuronpedia

    INDEX
    Explanations

    HTML and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bark
    -0.07
     perpetrators
    -0.07
     Ar
    -0.07
     André
    -0.06
    .J
    -0.06
     TA
    -0.06
     Ben
    -0.06
     Ek
    -0.06
     Stitch
    -0.06
     Kem
    -0.06
    POSITIVE LOGITS
     можна
    0.07
    ydro
    0.07
     mó
    0.07
    уч
    0.06
     serm
    0.06
     어�
    0.06
    μη
    0.06
    .HtmlControls
    0.06
     зда
    0.06
    Coupon
    0.06
    Act Density 0.062%

    No Known Activations