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

    Neuronpedia

    INDEX
    Explanations

    code and references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apes
    -0.07
    โรค
    -0.07
    gener
    -0.07
    做大
    -0.06
    行业中
    -0.06
    الأر
    -0.06
     rave
    -0.06
    fdc
    -0.06
    -categories
    -0.06
     Bliss
    -0.06
    POSITIVE LOGITS
     jou
    0.07
     hei
    0.07
    Got
    0.07
     Standing
    0.07
     Cornell
    0.07
     tank
    0.06
     类
    0.06
    胜利
    0.06
     AssemblyCopyright
    0.06
     HER
    0.06
    Act Density 0.010%

    No Known Activations