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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash

    The neuron flags numeric and measurement‐related terms (e.g. distances, coordinates, radii, point counts) in geospatial query contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    yle
    -0.07
     cages
    -0.07
     永
    -0.06
     Луч
    -0.06
     mart
    -0.06
     것이
    -0.06
    猜
    -0.06
     angel
    -0.06
    .ci
    -0.06
     fold
    -0.06
    POSITIVE LOGITS
    DivElement
    0.08
     perché
    0.07
     setAddress
    0.07
     NSCoder
    0.06
    Commands
    0.06
     jedin
    0.06
    Typography
    0.06
     violently
    0.06
     specializing
    0.06
    udicots
    0.06
    Act Density 0.109%

    No Known Activations