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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pci
    -0.07
     مدى
    -0.07
     bí
    -0.07
    implement
    -0.07
    eń
    -0.07
    .Sqrt
    -0.06
     cov
    -0.06
    нской
    -0.06
    崆
    -0.06
    _RAM
    -0.06
    POSITIVE LOGITS
    !");↵
    0.07
    工作者
    0.07
     Horse
    0.07
    Bo
    0.07
    .Un
    0.07
    ']]↵
    0.07
     throughout
    0.07
    doing
    0.07
    '],
↵
    0.07
    Opts
    0.07
    Act Density 0.004%

    No Known Activations