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

    Neuronpedia

    INDEX
    Explanations

    144

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tar
    -0.09
     ўз
    -0.08
     FAR
    -0.07
    usan
    -0.07
     regal
    -0.07
    cam
    -0.07
    Tar
    -0.07
     liquids
    -0.07
     गरिएको
    -0.07
    respond
    -0.07
    POSITIVE LOGITS
     Eg
    0.09
     Sham
    0.08
    /pi
    0.08
    113
    0.08
    0.07
    meli
    0.07
    否
    0.07
     pretend
    0.07
    راه
    0.07
     Hel
    0.07
    Act Density 0.007%
    No Known Activations