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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riba
    -0.07
    FA
    -0.07
    aaaa
    -0.07
    FREE
    -0.07
     annually
    -0.06
    MA
    -0.06
    Avg
    -0.06
     IDb
    -0.06
    elled
    -0.06
    _Delete
    -0.06
    POSITIVE LOGITS
     may
    0.07
     enlightenment
    0.06
    稱
    0.06
     pork
    0.06
     lies
    0.06
    }-${
    0.06
     lie
    0.06
     AVC
    0.06
     arou
    0.06
     din
    0.06
    Act Density 0.018%

    No Known Activations