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

    Neuronpedia

    INDEX
    Explanations

    significant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     site
    -0.07
     DataColumn
    -0.07
    .Agent
    -0.07
    اصل
    -0.06
     Mumbai
    -0.06
     adres
    -0.06
    _within
    -0.06
    耶
    -0.06
    aac
    -0.06
     ↵            ↵
    -0.06
    POSITIVE LOGITS
    <Vec
    0.07
     мал
    0.06
    DEL
    0.06
    Sig
    0.06
    Topics
    0.06
     beverages
    0.06
    ,text
    0.06
    _GENERAL
    0.06
    NR
    0.06
    ivia
    0.06
    Act Density 0.002%

    No Known Activations