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

    Neuronpedia

    INDEX
    Explanations

    political/ideological

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ų
    -0.08
     payer
    -0.08
     pagando
    -0.08
     creditor
    -0.07
     bidder
    -0.07
     Société
    -0.07
     power
    -0.07
    _power
    -0.07
     Zahlungs
    -0.07
    _wait
    -0.07
    POSITIVE LOGITS
     воспит
    0.13
    培养
    0.12
     counseling
    0.11
     incul
    0.11
     ಶಿಕ್ಷಣ
    0.10
    교육
    0.10
    课程
    0.10
    教育
    0.10
     Counseling
    0.09
     التربية
    0.09
    Act Density 0.017%

    No Known Activations