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

    Neuronpedia

    INDEX
    Explanations

    HTML/XML tags, keywords, and structures indicative of structured data

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

    Code, brackets, or special characters

    np_acts-logits-general · gemini-2.0-flash

    enlightenment basics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.87
    dicionado
    -0.83
    InputBorder
    -0.82
     propOrder
    -0.81
    AutoresizingMask
    -0.78
     صوتيه
    -0.77
     purpoſe
    -0.77
     Efq
    -0.76
     ainfi
    -0.76
     ―――――
    -0.76
    POSITIVE LOGITS
    aarrggbb
    0.56
    –
    0.50
     bitte
    0.49
     U
    0.48
    бурга
    0.48
    --
    0.47
     “
    0.46
    AsUp
    0.45
     "
    0.44
    </b>
    0.44
    Act Density 4.068%

    No Known Activations