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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability

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

    "stable" or "stability"

    np_acts-logits-general · gemini-2.0-flash

    stable states and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rzez
    -0.48
    outh
    -0.45
    ers
    -0.44
     subprocess
    -0.41
    jungan
    -0.41
     different
    -0.40
    Jew
    -0.40
    cessite
    -0.40
    varargin
    -0.40
     each
    -0.39
    POSITIVE LOGITS
     stability
    1.16
     Stability
    1.16
    Stable
    1.16
     Stable
    1.16
     stable
    1.15
    Stability
    1.12
     stabil
    1.07
     estabilidad
    1.07
     stabilize
    1.07
     stabile
    1.04
    Act Density 0.209%

    No Known Activations