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

    Neuronpedia

    INDEX
    Explanations

    economics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jackson
    -0.07
     için
    -0.06
    Ben
    -0.06
     ATV
    -0.06
    Mayor
    -0.06
     Ben
    -0.06
     GameManager
    -0.06
     Mayor
    -0.06
     clashed
    -0.06
    _ne
    -0.06
    POSITIVE LOGITS
    ості
    0.07
     shaft
    0.07
     záz
    0.06
    xfd
    0.06
    uesta
    0.06
     管
    0.06
    _sr
    0.06
    anson
    0.06
     журн
    0.06
     enam
    0.06
    Act Density 0.027%

    No Known Activations