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

    Neuronpedia

    INDEX
    Explanations

    vector index distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atkins
    0.44
    Jasper
    0.44
     Jasper
    0.43
     Garner
    0.41
    韫
    0.41
     AUTHORS
    0.40
    ੂੰ
    0.39
    jazz
    0.39
    Semantic
    0.39
     Gwen
    0.39
    POSITIVE LOGITS
    index
    0.44
    flip
    0.44
    Index
    0.43
     distância
    0.43
     distances
    0.42
     billions
    0.42
    distance
    0.42
    INDEX
    0.41
     trillions
    0.41
    float
    0.40
    Act Density 0.016%

    No Known Activations