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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ох
    -0.08
     Entry
    -0.08
    -0.08
    ting
    -0.07
    °F
    -0.07
    .doc
    -0.07
     Employment
    -0.07
     Boarding
    -0.07
     Yi
    -0.07
     turma
    -0.07
    POSITIVE LOGITS
    edeut
    0.08
     redundant
    0.07
     الماء
    0.07
    لوك
    0.07
    outed
    0.07
     پانی
    0.07
     लोग
    0.07
    地下
    0.07
    arrison
    0.07
     }}
↵
    0.07
    Act Density 0.005%
    No Known Activations