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

    Neuronpedia

    INDEX
    Explanations

    pneumonia and related illnesses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ились
    -0.07
    unakan
    -0.06
     serv
    -0.06
    Moment
    -0.06
     escaping
    -0.06
    asers
    -0.06
    Matching
    -0.06
     gaining
    -0.06
    وذ
    -0.06
    Buf
    -0.06
    POSITIVE LOGITS
    녁
    0.07
     Leisure
    0.07
     Woodward
    0.06
    ###############################################################################↵
    0.06
     &↵
    0.06
     bm
    0.06
    (ValueError
    0.06
     kostenlose
    0.06
    219
    0.06
    ######↵
    0.06
    Act Density 0.012%

    No Known Activations