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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     existe
    -0.08
     Arte
    -0.07
     xx
    -0.07
     США
    -0.07
     Accum
    -0.07
    (REG
    -0.07
     Dubai
    -0.07
     lin
    -0.07
     amore
    -0.07
     cuid
    -0.07
    POSITIVE LOGITS
    ন
    0.07
    Transparent
    0.07
     imperial
    0.07
    簏
    0.07
    getOption
    0.07
    คอม
    0.07
    פן
    0.07
    يز
    0.07
    ---------------
    0.07
    폰
    0.06
    Act Density 0.002%

    No Known Activations