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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    افي
    -0.07
    _city
    -0.07
     eligibility
    -0.06
     trafficking
    -0.06
    (vol
    -0.06
    (__
    -0.06
     conviction
    -0.06
    _boost
    -0.06
     참
    -0.06
    ائيل
    -0.06
    POSITIVE LOGITS
     shook
    0.07
    tempt
    0.06
     kar
    0.06
    performance
    0.06
    わせ
    0.06
     subsidiaries
    0.06
    ious
    0.06
     кін
    0.06
     рань
    0.06
     юрид
    0.06
    Act Density 0.003%

    No Known Activations