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

    Neuronpedia

    INDEX
    Explanations

    Interval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presidents
    -0.08
    ouflage
    -0.08
     showcased
    -0.07
     PS
    -0.07
     congr
    -0.07
     phot
    -0.07
    ，《
    -0.07
     rover
    -0.07
     któ
    -0.06
     PS
    -0.06
    POSITIVE LOGITS
    ічний
    0.08
     üretim
    0.06
    rahim
    0.06
     startTime
    0.06
    logfile
    0.06
    шли
    0.06
    病
    0.06
     TEMP
    0.06
    /span
    0.06
    fluence
    0.06
    Act Density 0.000%

    No Known Activations