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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drugs
    -0.06
    JP
    -0.06
    icides
    -0.06
    stice
    -0.06
     tractor
    -0.06
     mv
    -0.06
     Das
    -0.06
     afr
    -0.06
    432
    -0.06
    .DE
    -0.06
    POSITIVE LOGITS
    Arch
    0.07
    /stdc
    0.07
     edi
    0.06
     cloves
    0.06
     biển
    0.06
     नक
    0.06
    اوت
    0.06
     모든
    0.06
     olay
    0.06
    <C
    0.06
    Act Density 0.076%

    No Known Activations