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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or symbols

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

    closing structural delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pecabe
    -1.01
    تقاوى
    -0.94
    iſen
    -0.92
    -0.91
     témoig
    -0.89
    ſelves
    -0.89
    脚注の使い方
    -0.87
    ſicht
    -0.86
    postsleuth
    -0.86
     فريبيس
    -0.85
    POSITIVE LOGITS
    s
    0.72
    </em>
    0.64
    </i>
    0.62
    </sup>
    0.62
    </sub>
    0.59
    }$
    0.55
    </b>
    0.52
    }}$
    0.52
    ]}$
    0.51
     )}$
    0.51
    Act Density 0.006%

    No Known Activations