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

    Neuronpedia

    INDEX
    Explanations

    consistently repeated phrases relating to stability

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

    steady

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.56
    URLException
    -0.55
    JMenuItem
    -0.54
     Müll
    -0.53
     Airports
    -0.53
    PageModule
    -0.50
     bathrooms
    -0.49
    woff
    -0.48
     Sulphur
    -0.48
     Kork
    -0.47
    POSITIVE LOGITS
     Steady
    1.24
    Steady
    1.16
    steady
    1.13
     steady
    1.11
    teady
    0.91
     steadily
    0.84
     Stead
    0.73
     stea
    0.71
    稳
    0.65
     stead
    0.65
    Act Density 0.003%

    No Known Activations