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

    Neuronpedia

    INDEX
    Explanations

    changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distancing
    -0.07
    ってい
    -0.07
    /rem
    -0.06
    ERV
    -0.06
    reserved
    -0.06
    -0.06
     Orc
    -0.06
     Trav
    -0.06
     redirection
    -0.06
     warrior
    -0.06
    POSITIVE LOGITS
     concert
    0.08
    imonials
    0.07
     Sears
    0.06
     кон
    0.06
     adip
    0.06
     CDs
    0.06
     Někter
    0.06
    hydro
    0.06
    diğini
    0.06
     {}.
    0.06
    Act Density 0.025%

    No Known Activations