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

    Neuronpedia

    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ชอบ
    -0.06
     Seasons
    -0.06
    inesis
    -0.06
    scoped
    -0.06
    Resources
    -0.06
    никами
    -0.06
    ozřejmě
    -0.06
    ندا
    -0.06
    dao
    -0.06
    tableView
    -0.06
    POSITIVE LOGITS
     HP
    0.07
    -caption
    0.06
    Started
    0.06
     металли
    0.06
     REPL
    0.06
    declare
    0.06
     validator
    0.06
     western
    0.06
    	reset
    0.06
     uttered
    0.06
    Act Density 0.232%

    No Known Activations