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

    Neuronpedia

    INDEX
    Explanations

    Discrediting arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fit
    -0.06
     máy
    -0.06
     Crane
    -0.06
     metrics
    -0.06
     exploiting
    -0.06
     travail
    -0.06
     youre
    -0.06
     acción
    -0.06
    確認
    -0.06
     Spark
    -0.06
    POSITIVE LOGITS
    Accordion
    0.06
    toEqual
    0.06
    ,'
    0.06
     Serializable
    0.06
    EV
    0.06
     nons
    0.06
     actor
    0.06
    tokenId
    0.06
    .AddScoped
    0.06
    .setDefault
    0.06
    Act Density 0.046%

    No Known Activations