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

    Neuronpedia

    INDEX
    Explanations

    Legal arguments/court cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     नय
    -0.06
     recursion
    -0.06
    ुद
    -0.06
    ]=-
    -0.06
     paternal
    -0.06
    ersive
    -0.06
    .***
    -0.06
    ']."
    -0.06
     Table
    -0.06
    anguages
    -0.06
    POSITIVE LOGITS
     anh
    0.06
     티
    0.06
    링
    0.06
     Kata
    0.06
     аж
    0.06
    كور
    0.06
    AUT
    0.06
     مشخص
    0.06
    باب
    0.06
    _pcm
    0.05
    Act Density 0.011%

    No Known Activations