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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Delayed
    -0.07
    ها
    -0.06
    367
    -0.06
     lai
    -0.06
     Filme
    -0.06
     negro
    -0.06
     chickens
    -0.06
    asher
    -0.06
     orbs
    -0.06
    oldur
    -0.06
    POSITIVE LOGITS
     table
    0.08
     tables
    0.07
     tav
    0.07
     görül
    0.07
     마법
    0.07
     carnival
    0.06
     γε
    0.06
     Cor
    0.06
     professor
    0.06
     Marketplace
    0.06
    Act Density 0.006%

    No Known Activations