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

    Neuronpedia

    INDEX
    Explanations

    tricks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Empty
    -0.07
     dirty
    -0.07
     luggage
    -0.06
     extinct
    -0.06
    .**************↵
    -0.06
     given
    -0.06
     concerned
    -0.06
    oty
    -0.06
    uyến
    -0.06
     various
    -0.06
    POSITIVE LOGITS
    mill
    0.06
     cont
    0.06
    -even
    0.06
     nederland
    0.06
    ='".$
    0.06
     espionage
    0.06
     oracle
    0.06
    ！」
    0.06
     thé
    0.06
     awe
    0.06
    Act Density 0.052%

    No Known Activations