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

    Neuronpedia

    INDEX
    Explanations

    net carbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catalyzes
    0.54
     Eventually
    0.48
     noticias
    0.47
     transformación
    0.46
     页
    0.46
     首先
    0.46
     обеспечи
    0.45
    Eventually
    0.45
     กรณี
    0.44
     Özellikle
    0.43
    POSITIVE LOGITS
     sleep
    0.54
     populous
    0.48
    \%,
    0.47
    $",
    0.45
    :"",
    0.45
    !",
    0.45
    स्पर
    0.44
     "/",
    0.43
    們
    0.43
     Circular
    0.43
    Act Density 0.002%

    No Known Activations