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

    Neuronpedia

    INDEX
    Explanations

    image filtering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Congress
    -0.09
     COUNTY
    -0.08
    expense
    -0.07
     IRS
    -0.07
    .Many
    -0.07
     CFR
    -0.07
    _section
    -0.07
     lords
    -0.07
     dues
    -0.07
    郗
    -0.07
    POSITIVE LOGITS
    .api
    0.07
    죗
    0.07
    珸
    0.07
    ילת
    0.07
    好评
    0.07
    🗁
    0.07
     potentials
    0.07
     broken
    0.07
    מפגש
    0.07
     definitely
    0.06
    Act Density 0.011%

    No Known Activations