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

    Neuronpedia

    INDEX
    Explanations

    code definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sniper
    -0.06
     gunfire
    -0.06
     Charges
    -0.06
    .savefig
    -0.06
     Anxiety
    -0.06
     tabs
    -0.06
     Hawaii
    -0.06
    .Save
    -0.06
    renderer
    -0.06
    Performance
    -0.06
    POSITIVE LOGITS
     JQuery
    0.06
    irl
    0.06
     General
    0.06
     çıkar
    0.06
    \param
    0.06
     yayım
    0.06
    UART
    0.06
    uele
    0.06
     Roosevelt
    0.06
    uen
    0.06
    Act Density 0.016%

    No Known Activations