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

    Neuronpedia

    INDEX
    Explanations

    formal language and structure related to conclusions and summaries

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

    Follows names, titles, or codes

    np_acts-logits-general · gemini-2.0-flash

    reading specific publications or articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.86
    tagHelperRunner
    -0.85
    XmlAccessType
    -0.79
    fromnode
    -0.78
    fjspx
    -0.73
    #+#
    -0.73
    最快更新
    -0.70
    -0.68
    '}),
    -0.67
     dAtA
    -0.67
    POSITIVE LOGITS
     Also
    0.68
    READ
    0.64
     Moreover
    0.63
    Also
    0.63
     READ
    0.60
    RELATED
    0.59
    read
    0.57
     read
    0.57
     ALSO
    0.57
    Moreover
    0.56
    Act Density 0.055%

    No Known Activations