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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    меч
    -0.07
     společně
    -0.06
     letto
    -0.06
     Ад
    -0.06
    ลด
    -0.06
    .dim
    -0.06
    enido
    -0.06
     destructor
    -0.06
    зано
    -0.06
    jos
    -0.06
    POSITIVE LOGITS
     airing
    0.07
    executable
    0.07
     late
    0.07
    Padding
    0.07
     ],↵
    0.07
    852
    0.07
    ）。↵↵
    0.06
     lastName
    0.06
    ette
    0.06
    .assertNot
    0.06
    Act Density 0.007%

    No Known Activations