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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mężczy
    -0.07
     Pharmac
    -0.07
    文化和
    -0.07
     Luc
    -0.07
    torch
    -0.06
     Library
    -0.06
    tax
    -0.06
    慢慢
    -0.06
     memberId
    -0.06
    prowadzi
    -0.06
    POSITIVE LOGITS
     ц
    0.07
     resultados
    0.07
    çãeste
    0.07
    ção
    0.07
     Crop
    0.07
    (MSG
    0.07
    azer
    0.07
     peso
    0.07
    iltro
    0.07
    rze
    0.07
    Act Density 0.006%

    No Known Activations