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

    Neuronpedia

    INDEX
    Explanations

    structures or syntax resembling programming or markup language elements

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

    Followed by "<" or "'" characters

    np_acts-logits-general · gemini-2.0-flash

    Closing XML/HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.06
     Majefty
    -1.05
     ་་
    -1.02
     Monfieur
    -1.02
     Anſ
    -1.01
    таратура
    -1.00
     faſt
    -0.98
     ſever
    -0.94
     Houſe
    -0.94
     houſe
    -0.94
    POSITIVE LOGITS
    <eos>
    0.83
    ↵
    0.78
    </blockquote>
    0.77
    </code>
    0.73
    </
    0.72
    }
    0.66
     
    0.66
    )
    0.65
    </i>
    0.65
    ↵↵
    0.64
    Act Density 1.049%

    No Known Activations