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

    Neuronpedia

    INDEX
    Explanations

    mergers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ന
    -0.08
     Entity
    -0.07
    気が
    -0.07
    쏭
    -0.07
    .Pending
    -0.07
    排气
    -0.07
    主编
    -0.07
     appearance
    -0.07
     gender
    -0.07
     bmi
    -0.07
    POSITIVE LOGITS
    exc
    0.07
    特别是在
    0.07
     kicks
    0.06
     greens
    0.06
    ływ
    0.06
     włos
    0.06
    Associ
    0.06
    تخل
    0.06
    學習
    0.06
    brew
    0.06
    Act Density 0.045%

    No Known Activations