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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     possession
    -0.08
    IVITY
    -0.07
    imetype
    -0.07
    commit
    -0.07
     WORK
    -0.06
     Mikhail
    -0.06
     المت
    -0.06
    akh
    -0.06
     adopt
    -0.06
    ilty
    -0.06
    POSITIVE LOGITS
     draped
    0.07
     بل
    0.07
     servic
    0.06
    真的
    0.06
     Buccaneers
    0.06
     realidad
    0.06
    Fld
    0.06
     ILogger
    0.06
     ReferentialAction
    0.06
     условиях
    0.06
    Act Density 0.001%

    No Known Activations