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

    Neuronpedia

    INDEX
    Explanations

    returns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canadiens
    -0.07
     traveller
    -0.07
     mirrors
    -0.07
     EXPER
    -0.06
     против
    -0.06
     Milton
    -0.06
    Ke
    -0.06
     Sue
    -0.06
    Track
    -0.06
     Aut
    -0.06
    POSITIVE LOGITS
     dresses
    0.07
    estival
    0.07
    _ss
    0.07
     khác
    0.06
    asyon
    0.06
     allegedly
    0.06
    ้ท
    0.06
     ulaş
    0.06
     blooms
    0.06
     writeln
    0.06
    Act Density 0.014%

    No Known Activations