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

    Neuronpedia

    INDEX
    Explanations

    numbers after words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nbd
    0.49
     belangrijk
    0.47
     UserManager
    0.46
     velocidades
    0.46
     increment
    0.45
     obligaciones
    0.44
     dẫn
    0.44
     nrow
    0.44
     couldn
    0.44
     instalaciones
    0.44
    POSITIVE LOGITS
    ר
    0.58
    an
    0.48
    C
    0.47
    France
    0.46
    ু
    0.46
    Commerce
    0.46
    commutative
    0.45
    ตี
    0.45
    ে
    0.45
    Traité
    0.44
    Act Density 0.001%

    No Known Activations