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

    Neuronpedia

    INDEX
    Explanations

    Punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /XML
    -0.07
     insect
    -0.07
    atics
    -0.06
     晴
    -0.06
    Tor
    -0.06
     답
    -0.06
     pu
    -0.06
     onBackPressed
    -0.06
    _bw
    -0.06
     Indust
    -0.06
    POSITIVE LOGITS
     запас
    0.07
    BC
    0.06
     بعد
    0.06
    ；↵
    0.06
     familia
    0.06
    不能
    0.06
     Spacer
    0.06
    -Americ
    0.06
    profession
    0.06
    ism
    0.06
    Act Density 0.000%

    No Known Activations