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

    Neuronpedia

    INDEX
    Explanations

    numerous instances of non-textual elements or formatting in the document

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

    legal references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jadx
    -0.63
    fillType
    -0.59
    ValueStyle
    -0.59
    AndEndTag
    -0.59
     թվական
    -0.57
    AxisSize
    -0.55
     AssemblyCulture
    -0.54
    ⓧ
    -0.53
    ãng
    -0.53
     Threat
    -0.52
    POSITIVE LOGITS
    2.19
     */
    0.53
    subsection
    0.52
    --*/
    0.52
    LikeLike
    0.49
    """)
    0.47
    ))->
    0.47
    }`).
    0.45
    )*/
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    Act Density 0.006%

    No Known Activations