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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and stabilization

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

    stability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.56
     mày
    -0.54
     congressman
    -0.52
    ROW
    -0.50
     Joe
    -0.49
    row
    -0.49
    joh
    -0.49
     Juan
    -0.48
    Juan
    -0.47
     Royce
    -0.47
    POSITIVE LOGITS
     stability
    2.06
     Stability
    2.02
    Stability
    1.95
    stability
    1.81
     STABILITY
    1.77
     stabilité
    1.67
     estabilidad
    1.55
     stable
    1.45
     Stable
    1.44
     stabilize
    1.44
    Act Density 0.014%

    No Known Activations