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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and stability evaluation in various systems

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

    stably or stable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.59
    Билгалдахарш
    -0.59
    SharedDtor
    -0.54
     lenker
    -0.50
    Jeografia
    -0.49
    URIComponent
    -0.48
    refour
    -0.47
     whereof
    -0.47
     Opp
    -0.46
     userID
    -0.46
    POSITIVE LOGITS
     stability
    1.63
     Stability
    1.63
     stable
    1.58
    Stability
    1.57
     stabil
    1.55
    Stable
    1.54
     Stable
    1.51
     STABILITY
    1.48
    stability
    1.46
    stable
    1.45
    Act Density 0.028%

    No Known Activations