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

    Neuronpedia

    INDEX
    Explanations

    technical problem solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olvency
    -0.07
     hver
    -0.06
     Bai
    -0.06
     Pont
    -0.06
    .Ap
    -0.06
     Col
    -0.06
    Ark
    -0.06
    _gt
    -0.06
     KK
    -0.06
     Kai
    -0.06
    POSITIVE LOGITS
     sna
    0.07
    ží
    0.07
    _sizes
    0.07
     invest
    0.06
    дов
    0.06
    heid
    0.06
    -names
    0.06
    ==========
    0.06
     aconte
    0.06
     veel
    0.06
    Act Density 0.179%

    No Known Activations