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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Inserted
    -0.06
    Game
    -0.06
     первой
    -0.06
    Officials
    -0.06
     웹사이트
    -0.06
    growth
    -0.06
     Century
    -0.06
    ication
    -0.06
     düzen
    -0.06
    öh
    -0.06
    POSITIVE LOGITS
    oked
    0.07
    거래
    0.06
     Pirate
    0.06
     Empresa
    0.06
     clit
    0.06
     scp
    0.06
     Intercept
    0.06
    .hero
    0.06
    +t
    0.05
     neuronal
    0.05
    Act Density 0.042%

    No Known Activations