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

    Neuronpedia

    INDEX
    Explanations

    terms related to root directories in file systems

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

    ROOT file paths and system identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.55
    PMailer
    -0.48
    routeProvider
    -0.46
     Photocase
    -0.44
     JADX
    -0.42
    EMPLO
    -0.42
    BufferException
    -0.42
    ISODE
    -0.40
     spasm
    -0.39
     end
    -0.39
    POSITIVE LOGITS
    ROOT
    2.70
     ROOT
    1.73
    roots
    0.99
    Roots
    0.96
     Roots
    0.95
    Root
    0.94
    getRoot
    0.88
    rooted
    0.87
    root
    0.85
     Root
    0.83
    Act Density 0.006%

    No Known Activations