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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Car
    -0.07
    	to
    -0.06
     scorn
    -0.06
    377
    -0.06
    theros
    -0.06
    TD
    -0.06
     teamed
    -0.06
    _True
    -0.06
    Card
    -0.06
     Não
    -0.06
    POSITIVE LOGITS
     fixes
    0.06
    shade
    0.06
     adolescents
    0.06
     Momentum
    0.06
     asthma
    0.06
    اون
    0.06
     Havana
    0.06
     Connections
    0.06
     вед
    0.06
     Appalachian
    0.06
    Act Density 0.018%

    No Known Activations