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

    Neuronpedia

    INDEX
    Explanations

    random snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    олько
    -0.06
     manifestations
    -0.06
    (Color
    -0.06
    tal
    -0.06
    \Traits
    -0.06
     سریال
    -0.06
    孤
    -0.06
     Coll
    -0.06
     jag
    -0.06
     뿐
    -0.06
    POSITIVE LOGITS
    자인
    0.07
     رع
    0.07
    itore
    0.06
    تش
    0.06
    řik
    0.06
    Roz
    0.06
     місті
    0.06
     موفق
    0.06
    athom
    0.06
    úi
    0.06
    Act Density 0.000%

    No Known Activations