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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üh
    -0.07
    -ф
    -0.06
    Secret
    -0.06
     وأ
    -0.06
    领
    -0.06
     гот
    -0.06
    intern
    -0.06
    魔法
    -0.06
     GA
    -0.06
    SBATCH
    -0.06
    POSITIVE LOGITS
     remove
    0.07
    -shell
    0.07
     olun
    0.06
    .music
    0.06
     add
    0.06
    show
    0.06
    @Column
    0.06
     numerous
    0.06
     cung
    0.06
    Robot
    0.06
    Act Density 0.008%

    No Known Activations