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

    Neuronpedia

    INDEX
    Explanations

    concepts related to consistency and reliability

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

    consistent or reproducible outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.47
     Belum
    -0.44
    anghai
    -0.43
     PopupWindow
    -0.42
     Versch
    -0.41
    StoryboardSegue
    -0.41
    BeginContext
    -0.40
    rangian
    -0.40
    asinya
    -0.40
     препратки
    -0.39
    POSITIVE LOGITS
     steady
    0.70
     consistently
    0.69
     Steady
    0.67
    穩定
    0.66
     estabilidad
    0.64
    Steady
    0.64
     Constant
    0.62
     stable
    0.62
    稳定
    0.61
    steady
    0.61
    Act Density 0.031%

    No Known Activations