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

    Neuronpedia

    INDEX
    Explanations

    Medical research paper references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getColumn
    -0.08
    景
    -0.07
    ptides
    -0.07
    
    -0.07
    35
    -0.07
    董
    -0.06
    PB
    -0.06
     Perez
    -0.06
    ksen
    -0.06
    思考
    -0.06
    POSITIVE LOGITS
     öff
    0.06
    urved
    0.06
    YST
    0.06
    (optarg
    0.06
    すす
    0.06
     argc
    0.06
     navbar
    0.05
    -->↵↵
    0.05
    ठ
    0.05
    FTA
    0.05
    Act Density 0.014%

    No Known Activations