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

    Neuronpedia

    INDEX
    Explanations

    references to file system paths or directory structures

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

    paths, routes, trails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setViewportView
    -0.45
    jalna
    -0.44
    eschön
    -0.40
    ️
    -0.40
    wolle
    -0.40
    े
    -0.39
    átka
    -0.37
     kyse
    -0.36
    化
    -0.36
    domada
    -0.36
    POSITIVE LOGITS
    paths
    1.65
     paths
    1.47
     Paths
    1.34
    Paths
    1.27
     pathways
    0.82
     routes
    0.82
     chemins
    0.79
     trails
    0.77
     Roads
    0.75
    roads
    0.73
    Act Density 0.014%

    No Known Activations