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

    Neuronpedia

    INDEX
    Explanations

    dangerous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nine
    -0.07
    Penn
    -0.07
     Ferrari
    -0.06
    084
    -0.06
    _MORE
    -0.06
    Forge
    -0.06
    Prov
    -0.06
     resistant
    -0.06
     beş
    -0.06
     Jerry
    -0.06
    POSITIVE LOGITS
     лют
    0.06
    (od
    0.06
     dnes
    0.06
    ware
    0.06
    summary
    0.06
    ational
    0.06
     گفت
    0.06
    _md
    0.06
     červ
    0.06
    кості
    0.06
    Act Density 0.179%

    No Known Activations