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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    yyy
    -0.06
    圭
    -0.06
     Zh
    -0.06
     Allied
    -0.06
    ício
    -0.06
    _share
    -0.06
     SAFE
    -0.06
    ศร
    -0.06
     Hale
    -0.06
    POSITIVE LOGITS
    mus
    0.06
     rapide
    0.05
    .btn
    0.05
     gamle
    0.05
    _version
    0.05
    _define
    0.05
    وقيت
    0.05
    .
    0.05
    ollapse
    0.05
     :＼
    0.05
    Act Density 1.001%

    No Known Activations