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

    Neuronpedia

    INDEX
    Explanations

    Software and online platforms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Poverty
    -0.09
     Pong
    -0.08
    Observ
    -0.08
     intangible
    -0.08
    Nag
    -0.07
    uiting
    -0.07
     árbit
    -0.07
     �
    -0.07
    .INT
    -0.07
     والمن
    -0.07
    POSITIVE LOGITS
    �
    0.10
     �
    0.09
    обходимо
    0.08
     heute
    0.08
    iane
    0.08
     Aktiv
    0.08
     махсус
    0.08
    œur
    0.08
    ‑
    0.08
    ähän
    0.08
    Act Density 0.194%

    No Known Activations