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

    Neuronpedia

    INDEX
    Explanations

    School meals, food programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bureaucracy
    -0.09
     Tinder
    -0.08
     dildo
    -0.07
     separat
    -0.07
     abrasive
    -0.07
     boilers
    -0.07
     Quartet
    -0.07
    acho
    -0.07
    �
    -0.07
    ixture
    -0.07
    POSITIVE LOGITS
     rebates
    0.09
     খাদ
    0.08
     amel
    0.08
    mst
    0.08
    福利
    0.08
     भोजन
    0.08
     Bolsa
    0.08
     খাব
    0.08
     commiss
    0.08
     uzt
    0.07
    Act Density 0.009%

    No Known Activations