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

    Neuronpedia

    INDEX
    Explanations

    Code for adding items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Languages
    -0.06
    _mu
    -0.06
    Calling
    -0.06
    maps
    -0.06
    534
    -0.06
     необходимости
    -0.06
     başladı
    -0.06
     Update
    -0.06
     Component
    -0.06
    True
    -0.06
    POSITIVE LOGITS
     IRC
    0.07
    γγ
    0.06
     leaning
    0.06
     hatta
    0.06
    ipher
    0.06
    роиз
    0.06
    ça
    0.06
     orderly
    0.06
     ص
    0.06
     JV
    0.06
    Act Density 0.035%

    No Known Activations