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
     dry
    -0.07
     corporations
    -0.07
     vegetable
    -0.07
    .Camera
    -0.06
     churches
    -0.06
    uka
    -0.06
    EntityType
    -0.06
    �
    -0.06
     amenities
    -0.06
     enrichment
    -0.06
    POSITIVE LOGITS
    Unlike
    0.07
     prank
    0.07
    ูล
    0.07
    _partitions
    0.07
    ToDelete
    0.07
     بحث
    0.06
     μην
    0.06
     эффек
    0.06
     리
    0.06
     increasingly
    0.06
    Act Density 0.028%

    No Known Activations