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

    Neuronpedia

    INDEX
    Explanations

    politics and elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ar
    -0.06
     yeşil
    -0.06
    \Auth
    -0.06
    iene
    -0.06
     moments
    -0.06
    _normal
    -0.06
    .gwt
    -0.05
    최
    -0.05
    ements
    -0.05
    фек
    -0.05
    POSITIVE LOGITS
     EACH
    0.07
    acağı
    0.07
    .CommandType
    0.07
    ////////////////////////////////////////////////////////////////////////////////↵
    0.07
    ">
↵
    0.07
     --------------------
    0.07
     ;)
    0.06
     тим
    0.06
    addock
    0.06
    '}}>↵
    0.06
    Act Density 0.018%

    No Known Activations