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

    Neuronpedia

    INDEX
    Explanations

    News/Politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trio
    -0.07
     enticing
    -0.06
     لكن
    -0.06
    jsonp
    -0.06
    969
    -0.06
    лара
    -0.06
     formed
    -0.06
    /request
    -0.06
    まま
    -0.06
    unately
    -0.05
    POSITIVE LOGITS
    illon
    0.07
     checkout
    0.07
    @Test
    0.07
     بل
    0.06
     вов
    0.06
     obsc
    0.06
    ég
    0.06
    zia
    0.06
    resi
    0.06
    ướng
    0.06
    Act Density 0.088%

    No Known Activations