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

    Neuronpedia

    INDEX
    Explanations

    obligation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    韧性
    -0.07
    red
    -0.07
     Hag
    -0.07
    abb
    -0.07
    PROP
    -0.06
     moving
    -0.06
    alex
    -0.06
    	sf
    -0.06
     Exists
    -0.06
    bag
    -0.06
    POSITIVE LOGITS
     {}).
    0.07
    rvine
    0.07
     укра
    0.07
     удалось
    0.07
    整个
    0.07
    imizeBox
    0.07
    ผลงาน
    0.06
     brigade
    0.06
    RICS
    0.06
    _CALC
    0.06
    Act Density 0.046%

    No Known Activations