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

    Neuronpedia

    INDEX
    Explanations

    white

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اسلام
    -0.06
     신규
    -0.06
     Noticed
    -0.06
     giữa
    -0.06
    ận
    -0.06
     ripped
    -0.06
     lived
    -0.06
    .coll
    -0.06
    _DOWN
    -0.06
    โน
    -0.05
    POSITIVE LOGITS
    .pattern
    0.08
    @\
    0.07
     Projectile
    0.07
     requiring
    0.07
    "data
    0.06
     aut
    0.06
    reature
    0.06
     野
    0.06
     dashboard
    0.06
    eslint
    0.06
    Act Density 0.005%

    No Known Activations