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

    Neuronpedia

    INDEX
    Explanations

    intersection and sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰
    0.52
    ется
    0.49
    </h3>
    0.46
    基づ
    0.46
    ρού
    0.46
    coefficient
    0.45
    ska
    0.44
     Karena
    0.44
    struktur
    0.44
    ﺟ
    0.44
    POSITIVE LOGITS
     Intersection
    0.52
     HERE
    0.52
     THAT
    0.52
     intersection
    0.49
     enorme
    0.48
     intersect
    0.48
     application
    0.48
     BRAND
    0.48
     ENTER
    0.47
     interment
    0.47
    Act Density 0.001%

    No Known Activations