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

    Neuronpedia

    INDEX
    Explanations

    HTML line breaks and structural markers in text

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

    HTML tags and LaTeX math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ロウィン
    -0.85
    iſen
    -0.85
     pérd
    -0.82
     incrí
    -0.79
     estadounid
    -0.79
     beſti
    -0.76
     témoig
    -0.75
    majánló
    -0.75
     increí
    -0.74
     geſch
    -0.74
    POSITIVE LOGITS
    br
    0.57
    <tr>
    0.42
    <bos>
    0.41
    n
    0.39
    Br
    0.39
    bl
    0.38
    ResumeLayout
    0.38
    BL
    0.37
     BL
    0.36
    H
    0.35
    Act Density 0.012%

    No Known Activations