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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     		↵
    -0.07
     Cover
    -0.07
    .Dom
    -0.07
     Cyril
    -0.06
    Amazon
    -0.06
     scenarios
    -0.06
     Inst
    -0.06
    "Do
    -0.06
    .register
    -0.06
     Sponsor
    -0.06
    POSITIVE LOGITS
    students
    0.07
    ництва
    0.07
    spi
    0.07
    881
    0.07
    เกษตร
    0.06
    _cre
    0.06
    uffman
    0.06
     tük
    0.06
     migration
    0.06
    rtle
    0.06
    Act Density 0.002%

    No Known Activations