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

    Neuronpedia

    INDEX
    Explanations

    terms related to neighbor relationships or proximity in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nearest neighbor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.65
    Autoritní
    -0.54
     Infórmanos
    -0.53
    Hochspringen
    -0.52
    /**
    -0.50
    tvguidetime
    -0.48
    transQ
    -0.47
    parsedMessage
    -0.46
    coke
    -0.46
     argc
    -0.46
    POSITIVE LOGITS
     Neighbor
    1.63
    neighbor
    1.60
    Neighbor
    1.55
     neighbor
    1.52
     Neighbors
    1.32
    Neighbors
    1.30
    neighbors
    1.27
    neighbour
    1.26
     neighbors
    1.25
     neighbour
    1.24
    Act Density 0.011%

    No Known Activations