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

    Neuronpedia

    INDEX
    Explanations

    terms related to robustness and immunity in various contexts

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

    robustness to changes in light and scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.39
     StringTokenizer
    -0.34
    sizeCache
    -0.33
     prêtres
    -0.33
    Xna
    -0.31
     świ
    -0.31
     Vorbild
    -0.31
    CELLANEOUS
    -0.30
    xase
    -0.30
    Amérique
    -0.30
    POSITIVE LOGITS
    TagMode
    0.72
     AssemblyCulture
    0.71
    Resistant
    0.56
     Resistant
    0.55
    CloseOperation
    0.54
     JpaRepository
    0.53
     AssemblyTitle
    0.53
    StructEnd
    0.52
    \{\\
    0.52
    resistant
    0.51
    Act Density 0.222%

    No Known Activations