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

    Neuronpedia

    INDEX
    Explanations

    phrases related to steps in processes or sequential actions

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

    "Step" or incremental actions

    np_acts-logits-general · gemini-2.0-flash

    step by step progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.89
     himo
    -0.81
    Obrázky
    -0.76
    MemoryWarning
    -0.75
     >=",
    -0.75
    DoubleQuotes
    -0.74
    -0.74
     فريبيس
    -0.72
    expandindo
    -0.72
    RectangleBorder
    -0.71
    POSITIVE LOGITS
     step
    1.26
     piece
    0.99
    step
    0.95
     layer
    0.94
     day
    0.94
     minute
    0.93
     Schritt
    0.93
     bit
    0.89
     Step
    0.88
     шаг
    0.88
    Act Density 0.370%

    No Known Activations