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

    Neuronpedia

    INDEX
    Explanations

    math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     egl
    -0.08
     urge
    -0.08
    */↵↵
    -0.08
     melod
    -0.08
     campos
    -0.08
     blaze
    -0.07
     temptation
    -0.07
    彩乐
    -0.07
     Sut
    -0.07
     anba
    -0.07
    POSITIVE LOGITS
     proportion
    0.10
     proportions
    0.10
     literacy
    0.09
    _population
    0.09
     ശതമ
    0.09
     tỷ
    0.09
     Literacy
    0.09
     населения
    0.09
    _prob
    0.09
     minorities
    0.08
    Act Density 0.036%

    No Known Activations