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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fright
    -0.07
     Peter
    -0.06
     astronauts
    -0.06
    чивается
    -0.06
     Included
    -0.06
    braco
    -0.06
    玛
    -0.06
     самом
    -0.06
     camps
    -0.06
     Scotch
    -0.06
    POSITIVE LOGITS
    Detector
    0.06
    :<
    0.06
     HY
    0.06
     اقدام
    0.06
     Gamb
    0.06
     evolves
    0.06
     Darwin
    0.06
     KA
    0.06
     Kat
    0.06
    Recommended
    0.06
    Act Density 0.029%

    No Known Activations