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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jian
    -0.06
     Filip
    -0.06
     inaccurate
    -0.06
    ância
    -0.06
     divides
    -0.06
     Wright
    -0.06
    죽
    -0.06
    -value
    -0.06
     voi
    -0.06
     So
    -0.06
    POSITIVE LOGITS
     وكانت
    0.08
    ософ
    0.07
     면
    0.07
     캐
    0.07
     CLIENT
    0.06
     hyperlink
    0.06
    Clients
    0.06
    حم
    0.06
     ENG
    0.06
    &↵
    0.06
    Act Density 0.023%

    No Known Activations