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

    Neuronpedia

    INDEX
    Explanations

    ATVs and motorcycles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WM
    -0.77
     Truck
    -0.75
     samochod
    -0.71
     şə
    -0.70
    ემ
    -0.69
    ᅳ
    -0.69
    blockSize
    -0.69
     bridge
    -0.68
    endaten
    -0.68
    шов
    -0.68
    POSITIVE LOGITS
     Polaris
    1.41
    Polar
    1.15
    polar
    0.92
     ATV
    0.87
    idios
    0.82
     Salford
    0.82
     Kawasaki
    0.81
     clutching
    0.79
     Baylor
    0.78
     XP
    0.77
    Act Density 0.009%

    No Known Activations