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

    Neuronpedia

    INDEX
    Explanations

    Complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -eff
    -0.06
    шку
    -0.06
     Maui
    -0.06
    hec
    -0.06
     CSI
    -0.06
     pups
    -0.06
     Goldberg
    -0.06
     Куб
    -0.06
    主
    -0.06
     MU
    -0.06
    POSITIVE LOGITS
    -standing
    0.07
    <footer
    0.07
    �单
    0.07
     varias
    0.07
    การท
    0.06
    .iterator
    0.06
    нівер
    0.06
    .expand
    0.06
    Chocolate
    0.06
    shan
    0.06
    Act Density 0.018%

    No Known Activations