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

    Neuronpedia

    INDEX
    Explanations

    terms related to maintaining or preserving a state or condition

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

    after forms of "maintain"

    np_acts-logits-general · gemini-2.0-flash

    maintaining a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.83
    windowFixed
    -0.75
     AssemblyCulture
    -0.74
    JspWriter
    -0.70
    tagext
    -0.65
     ModelExpression
    -0.64
    qrstuvwxyz
    -0.64
     ujednoznacz
    -0.64
    serviceWorker
    -0.64
    migrationBuilder
    -0.64
    POSITIVE LOGITS
    keep
    0.71
     Kept
    0.71
    不变
    0.70
     integrity
    0.69
     steady
    0.69
     momentum
    0.68
     vigilance
    0.66
     homeostasis
    0.66
     constant
    0.65
     secrecy
    0.63
    Act Density 0.125%

    No Known Activations