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

    Neuronpedia

    INDEX
    Explanations

    political

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eliminating
    -0.07
     minut
    -0.06
     counted
    -0.06
     invent
    -0.06
    ์ว
    -0.06
    _type
    -0.06
     خ
    -0.06
     multiplying
    -0.06
    kowski
    -0.06
     zá
    -0.06
    POSITIVE LOGITS
     politics
    0.07
     political
    0.07
    kili
    0.07
     Left
    0.07
    .utility
    0.07
     ~~
    0.07
     policies
    0.07
     Politics
    0.06
    ]!='
    0.06
     Judicial
    0.06
    Act Density 0.024%

    No Known Activations