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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Early
    -0.07
     pursue
    -0.07
    brates
    -0.07
    ۶
    -0.07
    anes
    -0.07
     Numerous
    -0.07
     day
    -0.06
    UES
    -0.06
     něho
    -0.06
     Reeves
    -0.06
    POSITIVE LOGITS
     dagger
    0.07
     Prostit
    0.07
    lu
    0.06
    111
    0.06
    	lua
    0.06
     Histogram
    0.06
    Politics
    0.06
     совет
    0.06
     QCOMPARE
    0.06
    #undef
    0.06
    Act Density 0.117%

    No Known Activations