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

    Neuronpedia

    INDEX
    Explanations

    several

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    迢
    -0.08
    /errors
    -0.07
     nostalgia
    -0.07
    iced
    -0.07
     or
    -0.07
    utility
    -0.07
    endency
    -0.07
    eros
    -0.07
    ième
    -0.06
    kategori
    -0.06
    POSITIVE LOGITS
     Lau
    0.09
    化学
    0.07
    금융
    0.07
    大方
    0.07
    投行
    0.07
     zoo
    0.07
    _study
    0.07
     Zhu
    0.07
     stricter
    0.07
    浇
    0.07
    Act Density 0.148%

    No Known Activations