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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Asc
    -0.07
     waivers
    -0.07
     recruiters
    -0.06
     The
    -0.06
    =").
    -0.06
      	↵
    -0.06
     جهانی
    -0.06
     sandals
    -0.06
     ف
    -0.06
    说的
    -0.06
    POSITIVE LOGITS
    htags
    0.08
    torrent
    0.06
    TX
    0.06
    <hr
    0.06
    limited
    0.06
     Jud
    0.06
     modo
    0.06
    abit
    0.06
    ertype
    0.06
    oco
    0.06
    Act Density 0.132%

    No Known Activations