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

    Neuronpedia

    INDEX
    Explanations

    quality/excellence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     household
    -0.07
     mine
    -0.07
     plates
    -0.06
     directors
    -0.06
     natur
    -0.06
     deviation
    -0.06
     nightmare
    -0.06
     mosque
    -0.06
     integers
    -0.06
     deviations
    -0.06
    POSITIVE LOGITS
    .il
    0.06
    MPI
    0.06
     SEXP
    0.06
    :url
    0.06
    ,G
    0.06
    Э
    0.06
    	dispatch
    0.06
    torrent
    0.06
    П
    0.06
    ektör
    0.06
    Act Density 0.042%

    No Known Activations