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

    Neuronpedia

    INDEX
    Explanations

    employee empowerment/decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CASA
    -0.09
     divides
    -0.08
     presença
    -0.08
     está
    -0.07
     planeta
    -0.07
     estar
    -0.07
     künst
    -0.07
     ಪ್ರತ
    -0.07
    ăr
    -0.07
     CHANNEL
    -0.07
    POSITIVE LOGITS
     discretion
    0.14
     autonomy
    0.13
     самостоятельно
    0.12
    自主
    0.12
     автоном
    0.11
     liberties
    0.11
     autonomía
    0.11
     tailoring
    0.11
     самостоятель
    0.10
     discretionary
    0.10
    Act Density 0.053%

    No Known Activations