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

    Neuronpedia

    INDEX
    Explanations

    fuel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atan
    -0.08
    atte
    -0.07
    ickname
    -0.07
    rough
    -0.07
    -white
    -0.07
    8
    -0.07
    asd
    -0.07
     licking
    -0.07
     notices
    -0.07
    عت
    -0.07
    POSITIVE LOGITS
     fuel
    0.20
     Fuel
    0.15
     fuels
    0.15
    fuel
    0.14
    Fuel
    0.11
     fueled
    0.10
    燃
    0.09
     Fu
    0.08
    UEL
    0.07
    Pel
    0.07
    Act Density 0.008%

    No Known Activations