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

    Neuronpedia

    INDEX
    Explanations

    Abbreviated company names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Schedulers
    -0.08
    ieu
    -0.07
    สร
    -0.07
     gez
    -0.07
    누
    -0.06
    in
    -0.06
    Hibernate
    -0.06
     Extended
    -0.06
    Blueprint
    -0.06
    Sales
    -0.06
    POSITIVE LOGITS
     bağımsız
    0.07
     Mos
    0.06
     RAND
    0.06
    (init
    0.06
     동안
    0.06
     ان
    0.06
    (vars
    0.06
    Mos
    0.06
    fetch
    0.06
    .salary
    0.06
    Act Density 0.031%

    No Known Activations