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

    Neuronpedia

    INDEX
    Explanations

    various types of code termination characters and structures, indicating the end of code blocks or statements

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

    Code snippets (mostly C-like syntax)

    np_acts-logits-general · gemini-2.0-flash

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     son
    -0.55
     Son
    -0.51
    شع
    -0.50
     component
    -0.49
     kính
    -0.49
    Cubit
    -0.49
    皙
    -0.48
     objective
    -0.46
    )|\
    -0.46
    roch
    -0.45
    POSITIVE LOGITS
    saraba
    0.73
     تضيفلها
    0.71
    HostException
    0.70
    QMetaType
    0.66
    كويكب
    0.65
    encodeWith
    0.65
    StoryboardSegue
    0.64
    CloseOperation
    0.63
     postIndex
    0.62
     Wikimedijinoj
    0.61
    Act Density 0.052%

    No Known Activations