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

    Neuronpedia

    INDEX
    Explanations

    bridge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     значение
    -0.07
     ప్రత
    -0.07
     manages
    -0.07
    ography
    -0.07
    teriors
    -0.07
     storage
    -0.07
     infrared
    -0.07
     значения
    -0.07
     וכו
    -0.07
    מ
    -0.07
    POSITIVE LOGITS
     Díaz
    0.10
    /comments
    0.09
     Cheer
    0.09
     Viral
    0.09
     Fur
    0.09
     Vocal
    0.09
     Clara
    0.09
     Lowell
    0.09
     Waterloo
    0.08
    Lovely
    0.08
    Act Density 0.002%

    No Known Activations