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

    Neuronpedia

    INDEX
    Explanations

    Buddha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plausible
    -0.07
    ܢ
    -0.07
    .Index
    -0.07
    变身
    -0.07
    -standard
    -0.07
     getMenu
    -0.07
     garbage
    -0.07
    ($_
    -0.06
    asmine
    -0.06
    日正式
    -0.06
    POSITIVE LOGITS
    hurst
    0.08
     الأعمال
    0.08
     therapeutic
    0.07
     Surg
    0.07
     Wool
    0.07
    (drop
    0.07
    ื่
    0.07
    simp
    0.07
    歩
    0.07
    ham
    0.07
    Act Density 0.008%

    No Known Activations