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

    Neuronpedia

    INDEX
    Explanations

    class of service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    0.69
    Sin
    0.64
    Post
    0.61
    的
    0.61
    Info
    0.55
    Mystery
    0.55
    (
    0.55
    Places
    0.55
    <
    0.55
    v
    0.54
    POSITIVE LOGITS
     tanned
    0.62
     👌
    0.61
     asientos
    0.61
     ойнотуу
    0.60
     overruled
    0.60
     queued
    0.58
    ólnie
    0.58
     couche
    0.57
     እድ
    0.57
    elijkheid
    0.57
    Act Density 0.006%

    No Known Activations