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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code snippets related to programming and system configurations

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

    file paths and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.43
     MainAxisSize
    -0.43
    Portale
    -0.42
     informée
    -0.41
    новништво
    -0.39
    ########.
    -0.39
    IVEREF
    -0.38
    作
    -0.38
     démo
    -0.37
    mtable
    -0.37
    POSITIVE LOGITS
     path
    0.72
    path
    0.69
     Path
    0.68
    Path
    0.67
     PATH
    0.57
    路径
    0.57
     paths
    0.56
     Paths
    0.56
    PATH
    0.55
     pathway
    0.55
    Act Density 0.006%

    No Known Activations