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

    Neuronpedia

    INDEX
    Explanations

    racing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    潾
    0.54
    図書館
    0.52
    縄
    0.51
    🚶
    0.48
    悖
    0.45
    論文
    0.44
    Tarea
    0.44
    IndexPath
    0.43
     бібліоте
    0.43
     ちゃう
    0.43
    POSITIVE LOGITS
     racing
    1.95
     motorsport
    1.78
     racers
    1.68
     Racing
    1.67
     Motorsport
    1.57
     racer
    1.56
    racing
    1.52
     race
    1.51
    Racing
    1.48
     raced
    1.40
    Act Density 0.017%

    No Known Activations