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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ayı
    -0.08
    医疗
    -0.07
    oeff
    -0.07
    療
    -0.07
    ymph
    -0.07
     monarchy
    -0.07
     dünyan
    -0.07
    睢
    -0.07
    ADIO
    -0.07
    当今
    -0.06
    POSITIVE LOGITS
     Burning
    0.08
     EZ
    0.07
    不错
    0.07
     constrained
    0.07
    Answers
    0.07
    (cb
    0.07
    親
    0.07
     Loose
    0.07
     Braz
    0.07
    修建
    0.06
    Act Density 0.103%

    No Known Activations