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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ko
    -0.06
     officer
    -0.06
     petrol
    -0.06
    \xe
    -0.06
    /Library
    -0.06
     judge
    -0.06
    ussen
    -0.06
    ified
    -0.06
     民
    -0.06
     terrorism
    -0.06
    POSITIVE LOGITS
    (show
    0.07
     проек
    0.07
     귀
    0.06
     amateurs
    0.06
     hete
    0.06
    _ARCHIVE
    0.06
    Really
    0.06
    .Dense
    0.06
    #ae
    0.06
    (lp
    0.06
    Act Density 0.066%

    No Known Activations