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

    Neuronpedia

    INDEX
    Explanations

    code compilation, multithreading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    氏
    -0.07
    _reduction
    -0.06
     domestically
    -0.06
    .gateway
    -0.06
     compliment
    -0.06
     EA
    -0.06
     lighten
    -0.06
     present
    -0.06
    !!.
    -0.06
    /"↵
    -0.06
    POSITIVE LOGITS
    ρ
    0.06
     Setter
    0.06
     бюджет
    0.06
    �
    0.06
    fillType
    0.06
     rež
    0.06
    ik
    0.06
     bondage
    0.06
    宿
    0.06
     tái
    0.06
    Act Density 0.023%

    No Known Activations