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

    Neuronpedia

    INDEX
    Explanations

    politics and government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hysteria
    -0.07
    _unref
    -0.07
    -book
    -0.07
     तर
    -0.06
     Rac
    -0.06
     forest
    -0.06
    dropout
    -0.06
    -med
    -0.06
    <Float
    -0.06
    τηκε
    -0.06
    POSITIVE LOGITS
    �
    0.06
    Number
    0.06
    juries
    0.06
    准备
    0.06
    分钟
    0.06
    number
    0.06
    �이
    0.06
    INNER
    0.06
     Swansea
    0.06
    52
    0.06
    Act Density 0.059%

    No Known Activations