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

    Neuronpedia

    INDEX
    Explanations

    Formal processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -election
    -0.07
    \",\
    -0.06
    Writes
    -0.06
     statically
    -0.06
     butt
    -0.06
     COPYING
    -0.06
    ovsky
    -0.06
     violent
    -0.06
     vaccinated
    -0.06
    isin
    -0.06
    POSITIVE LOGITS
    .ylabel
    0.06
    ัป
    0.06
     інших
    0.06
     isinstance
    0.06
    ページ
    0.06
    อาร
    0.06
     Ты
    0.06
    فران
    0.06
    quist
    0.06
    OrFail
    0.06
    Act Density 0.600%

    No Known Activations