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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    consume
    -0.08
    tagon
    -0.08
    capitalize
    -0.08
     ગુણ
    -0.08
    .consume
    -0.07
    ความ
    -0.07
    quality
    -0.07
     Meat
    -0.07
    reb
    -0.07
     לנו
    -0.07
    POSITIVE LOGITS
     vantage
    0.10
     rooftop
    0.09
     headquarters
    0.09
     roadside
    0.09
     rooft
    0.09
     sidelines
    0.09
    疆
    0.08
     helpless
    0.08
     terraces
    0.08
     accus
    0.08
    Act Density 0.042%

    No Known Activations